© 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. 8142
    Prev
    Next
    INDEX
    Explanations

    words associated with reviews and opinions

    oai_token-act-pair · 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
    licazione
    -0.70
     vectorielle
    -0.59
    styleable
    -0.56
    readystatechange
    -0.54
    }{||
    -0.54
    /**
    -0.54
    tagHelperRunner
    -0.53
    UAWEI
    -0.53
    //
    -0.52
    rikes
    -0.52
    POSITIVE LOGITS
    igsaw
    0.56
    ėms
    0.55
     transfieras
    0.54
     induct
    0.50
     resting
    0.48
     Jigsaw
    0.48
    chsel
    0.48
     مخطط
    0.48
    новниш
    0.48
     Вікіпе
    0.48
    Activations Density 8.424%

    No Known Activations