© 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. 8347
    Prev
    Next
    INDEX
    Explanations

    data in reports

    oai_token-act-pair · gemini-2.0-flash

    numerical results and statistics

    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
     open
    -0.97
    open
    -0.92
     OPEN
    -0.91
     Open
    -0.89
    Open
    -0.85
    OPEN
    -0.81
     öppna
    -0.73
     откры
    -0.69
     terbuka
    -0.69
    opend
    -0.66
    POSITIVE LOGITS
    wpi
    0.55
     Ceinture
    0.53
    owsky
    0.51
    pirable
    0.51
    TypedDataSet
    0.50
    monde
    0.50
    écution
    0.49
    stateMutability
    0.48
     cones
    0.47
     consciences
    0.46
    Activations Density 1.787%

    No Known Activations