© 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. 7043
    Prev
    Next
    INDEX
    Explanations

    political opinions and analysis

    oai_token-act-pair · gemini-2.0-flash

    technical or programming-related terms

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

    complex sentences

    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
     mentales
    -0.51
     ocupado
    -0.49
     urbanas
    -0.47
    covo
    -0.46
     végét
    -0.45
     mémor
    -0.45
     jiwa
    -0.45
     proposées
    -0.44
     sentiers
    -0.44
     amé
    -0.44
    POSITIVE LOGITS
     resourceCulture
    0.87
     تضيفلها
    0.81
    ANTLR
    0.77
    lgari
    0.75
     Reverso
    0.73
     >=",
    0.71
     صوتيه
    0.71
    IndentedString
    0.70
    sizeCache
    0.67
     CreateTagHelper
    0.67
    Activations Density 3.038%

    No Known Activations