© 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. 12839
    Prev
    Next
    INDEX
    Explanations

    words and phrases used when attempting to explain something

    oai_token-act-pair · gemini-2.0-flash

    risks to people

    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
     User
    -0.70
    voter
    -0.70
     Participant
    -0.69
     seller
    -0.69
     user
    -0.69
    Seller
    -0.68
     himſelf
    -0.68
    Estudiante
    -0.68
    Participant
    -0.67
     visitor
    -0.67
    POSITIVE LOGITS
    MigrationBuilder
    0.59
    yntaxException
    0.58
    devším
    0.52
     InputDecoration
    0.49
    Enllaces
    0.45
    endphp
    0.44
     nahilalakip
    0.44
    __*/
    0.44
     AssemblyCompany
    0.44
    帖最后由
    0.44
    Activations Density 2.425%

    No Known Activations