© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11843
    Prev
    Next
    INDEX
    Explanations

    lines that begin with the letter "H"

    oai_token-act-pair · gemini-2.0-flash

    H

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    XmlAccessType
    -0.49
    optString
    -0.45
    TestingModule
    -0.44
    nahm
    -0.43
    ριν
    -0.41
    osum
    -0.41
    HttpPut
    -0.40
    keteers
    -0.38
     lượt
    -0.38
    ticity
    -0.38
    POSITIVE LOGITS
    RenderAtEndOf
    0.68
    enumii
    0.66
     թվական
    0.64
     onPostExecute
    0.63
    новниш
    0.63
     nî
    0.62
    WebElementEntity
    0.61
     InkWell
    0.59
    المكان
    0.57
     FORCES
    0.57
    Activations Density 0.778%

    No Known Activations