© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1543
    Prev
    Next
    INDEX
    Explanations

    edits and revisions

    oai_token-act-pair · gemini-2.0-flash

    colon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     مرئيه
    -0.68
     يتيمه
    -0.67
    ItemBackground
    -0.60
    DockStyle
    -0.59
    ̍t
    -0.56
    يكب
    -0.54
    LElement
    -0.53
    Altre
    -0.53
    ędz
    -0.52
    ficult
    -0.52
    POSITIVE LOGITS
    Datuak
    0.74
    <bos>
    0.71
     Pingback
    0.69
     [*]
    0.58
    InjectAttribute
    0.57
     Offer
    0.55
    __':
    0.53
    ậy
    0.53
     edit
    0.52
    はじめに
    0.51
    Activations Density 1.069%

    No Known Activations