© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4780
    Prev
    Next
    INDEX
    Explanations

    mentions of educational institutions like academies and institutes

    oai_token-act-pair · gemini-2.0-flash

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    awtextra
    -0.71
    ClassNotFound
    -0.63
    ScopeManager
    -0.62
     HasFactory
    -0.60
     Cæsar
    -0.60
    ✨:
    -0.60
     OMITTED
    -0.60
    AccessorTable
    -0.59
    Tikang
    -0.59
    enumii
    -0.59
    POSITIVE LOGITS
    SqlClient
    0.65
     te
    0.53
    saraba
    0.49
     professional
    0.47
    irchen
    0.47
    TE
    0.46
    professional
    0.46
     calculated
    0.43
     Te
    0.43
    vádz
    0.43
    Activations Density 0.520%

    No Known Activations