© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2501
    Prev
    Next
    INDEX
    Explanations

    phrases expressing uncertainty or personal opinions

    oai_token-act-pair · gemini-2.0-flash

    as

    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
    <bos>
    -1.04
    RenderAtEndOf
    -0.64
    PreferredItem
    -0.60
    testens
    -0.58
    EndInit
    -0.55
     ExecuteAsync
    -0.50
    webElement
    -0.50
    Datuak
    -0.50
    WSGI
    -0.49
     setCode
    -0.47
    POSITIVE LOGITS
    帖最后由
    0.59
     виправивши
    0.57
     Vikipedi
    0.56
    qrstuvwxyz
    0.54
    bewerken
    0.53
     Propiedad
    0.53
     humide
    0.53
     ProtoMessage
    0.52
    saison
    0.51
    dengar
    0.51
    Activations Density 8.101%

    No Known Activations