© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10448
    Prev
    Next
    INDEX
    Explanations

    code license blurbs

    oai_token-act-pair · gemini-2.0-flash

    shared resources in code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     >=",
    -0.52
     BoxFit
    -0.50
    withIdentifier
    -0.46
     nahilalakip
    -0.46
     للمعارف
    -0.45
     виправивши
    -0.45
    ratulations
    -0.45
    ̈́
    -0.44
     يتيمه
    -0.44
    󠁢
    -0.43
    POSITIVE LOGITS
    <bos>
    1.01
    TagMode
    0.63
    <eos>
    0.51
     AssemblyTitle
    0.51
    AddField
    0.50
     consultato
    0.45
    </tr>
    0.44
    webElement
    0.44
    UserScript
    0.44
    UnknownFieldSet
    0.44
    Activations Density 0.384%

    No Known Activations