© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12853
    Prev
    Next
    INDEX
    Explanations

    proper nouns and related descriptive adjectives

    oai_token-act-pair · gemini-2.0-flash

    People and their roles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     AssemblyVersion
    -0.78
     Forumite
    -0.74
     BoxFit
    -0.74
    felves
    -0.74
     itſelf
    -0.71
     Monfieur
    -0.70
     raiſ
    -0.69
    ſelves
    -0.69
     Diſ
    -0.67
     purpoſe
    -0.67
    POSITIVE LOGITS
     I
    0.52
    ุง
    0.47
    ess
    0.45
    anke
    0.45
    toBe
    0.44
    ンダー
    0.42
    Affirmed
    0.42
     T
    0.42
     L
    0.41
    iske
    0.40
    Activations Density 2.200%

    No Known Activations