© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11583
    Prev
    Next
    INDEX
    Explanations

    references to the concept of likelihood or probability

    oai_token-act-pair · gemini-2.0-flash

    probability

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    principalColumn
    -0.59
    webElementXpaths
    -0.55
     CURIAM
    -0.52
    igshid
    -0.51
    ioli
    -0.48
    CodedInputStream
    -0.46
    Становништво
    -0.45
     للمعارف
    -0.44
     post
    -0.44
     Horne
    -0.43
    POSITIVE LOGITS
     Efq
    0.74
     myſelf
    0.68
     fometimes
    0.68
     Occurrence
    0.63
     ſhe
    0.63
     preſent
    0.62
     occurrence
    0.61
     successful
    0.60
     правило
    0.59
     ModelExpression
    0.59
    Activations Density 0.794%

    No Known Activations