© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12469
    Prev
    Next
    INDEX
    Explanations

    text related to tabletop role-playing games

    oai_token-act-pair · gemini-2.0-flash

    Miscellaneous text/code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     estekak
    -0.74
     segno
    -0.54
     ostavi
    -0.54
    NameInMap
    -0.54
     plate
    -0.51
    IBOutlet
    -0.50
    plates
    -0.50
    EFAULT
    -0.50
    actionMode
    -0.50
    Hentet
    -0.50
    POSITIVE LOGITS
    enumi
    0.54
     مشين
    0.52
     role
    0.52
    RenderAtEndOf
    0.52
     Paddle
    0.50
     Role
    0.50
     uParam
    0.50
    PageIndex
    0.49
    তথ্যসূত্র
    0.49
    orsese
    0.49
    Activations Density 1.577%

    No Known Activations