© 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. 2849
    Prev
    Next
    INDEX
    Explanations

    descriptions of skills and items in a game, possibly an RPG

    oai_token-act-pair · gemini-2.0-flash

    kyutama and related objects

    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
    RTLR
    -0.57
     SEDS
    -0.56
    batore
    -0.54
     initComponents
    -0.54
    ngdoc
    -0.52
    artiges
    -0.52
    rawDesc
    -0.51
     lenker
    -0.51
    bootstrapcdn
    -0.50
    WebMethod
    -0.50
    POSITIVE LOGITS
    findpost
    0.67
     AttributeSet
    0.59
    hes
    0.54
     AspNetCore
    0.53
     chân
    0.51
    ⓧ
    0.51
     tege
    0.50
    LoadBalancer
    0.49
    SharedCtor
    0.49
     liev
    0.49
    Activations Density 7.048%

    No Known Activations