© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4908
    Prev
    Next
    INDEX
    Explanations

    various units of measurement, especially those in the context of programming and genetics

    oai_token-act-pair · gemini-2.0-flash

    files sizes/dimensions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    <bos>
    -1.16
     oprot
    -0.96
    RTDA
    -0.89
    MigrationBuilder
    -0.85
     nakalista
    -0.82
    первых
    -0.82
     Paglinawan
    -0.81
    LookAnd
    -0.78
    ResumeLayout
    -0.78
     ***!
    -0.77
    POSITIVE LOGITS
    depend
    0.43
     Fringe
    0.41
     anche
    0.41
     Later
    0.40
     zabaw
    0.40
    cid
    0.39
    ãng
    0.38
    ensi
    0.38
     Incluso
    0.38
     Leit
    0.38
    Activations Density 0.895%

    No Known Activations