© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9102
    Prev
    Next
    INDEX
    Explanations

    words or short phrases used in sexually explicit writing

    oai_token-act-pair · gemini-2.0-flash

    technical and programming-related terms

    np_token-act-pair-logits · gpt-4o-mini

    medical/technical writing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kirja
    -0.53
     caractère
    -0.50
     actualizaciones
    -0.47
     decorativas
    -0.47
     navideñas
    -0.45
     plă
    -0.44
     gesteld
    -0.44
     graciosos
    -0.44
     automatiques
    -0.44
     métallique
    -0.43
    POSITIVE LOGITS
    RegressionTest
    0.87
     defaultstate
    0.85
     الرياضيه
    0.79
     CreateTagHelper
    0.79
     cherchés
    0.74
    SequentialGroup
    0.72
    WithIOException
    0.71
     ostavi
    0.71
     wireType
    0.67
    stylers
    0.66
    Activations Density 3.961%

    No Known Activations