© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15301
    Prev
    Next
    INDEX
    Explanations

    code, mostly Java or Javascript, with some math operations and array indexing

    oai_token-act-pair · gemini-2.0-flash

    plus/minus

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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>
    -0.53
    upassen
    -0.42
    jsonwebtoken
    -0.41
     book
    -0.41
    ių
    -0.39
     buchen
    -0.38
     acum
    -0.38
    Continue
    -0.37
    тиза
    -0.37
     Gu
    -0.36
    POSITIVE LOGITS
    tvguidetime
    0.80
    extAlignment
    0.73
    存于互联网档案馆
    0.71
     dezelve
    0.71
    AddTagHelper
    0.71
     >=",
    0.70
     SqlCommand
    0.69
     IBOutlet
    0.69
     createSprite
    0.69
    WireFormatLite
    0.67
    Activations Density 5.289%

    No Known Activations