© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10019
    Prev
    Next
    INDEX
    Explanations

    numerical data and references to scientific publications

    oai_token-act-pair · gemini-2.0-flash

    scientific/technical writing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     ་་
    -1.01
     itſelf
    -0.97
     faſt
    -0.90
     myſelf
    -0.90
    \<^
    -0.90
     Houſe
    -0.87
     purpoſe
    -0.87
     houſe
    -0.87
     Majefty
    -0.86
    NUMX
    -0.82
    POSITIVE LOGITS
     Or
    0.43
    providedIn
    0.40
     But
    0.37
     or
    0.36
     One
    0.35
    PYX
    0.35
    WebMethod
    0.34
     OR
    0.34
    ises
    0.32
     And
    0.32
    Activations Density 25.388%

    No Known Activations