© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3714
    Prev
    Next
    INDEX
    Explanations

    snippets from online forums or help requests

    oai_token-act-pair · gemini-2.0-flash

    !

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     då
    -0.44
    Solución
    -0.44
     dAtA
    -0.44
    SqlClient
    -0.43
    nvarchar
    -0.42
    limus
    -0.42
    南浔
    -0.41
     kilometres
    -0.41
    出版年
    -0.40
    fahrung
    -0.40
    POSITIVE LOGITS
    TagMode
    0.81
     myſelf
    0.79
     poffible
    0.78
    XmlAccessorType
    0.74
     Monfieur
    0.73
     itſelf
    0.69
    IsMutable
    0.69
     Majefty
    0.68
     poffe
    0.67
     TextAppearance
    0.66
    Activations Density 0.668%

    No Known Activations