© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12276
    Prev
    Next
    INDEX
    Explanations

    words with high sentiment polarity that are related to positive reviews or recommendations, and applies a boost to contexts where it is addressing the person being reviewed directly.

    oai_token-act-pair · gemini-2.0-flash

    re

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    eapp
    -0.49
     bra
    -0.47
    وجد
    -0.47
     Gram
    -0.45
    نه
    -0.44
    boy
    -0.44
    clar
    -0.44
     nhà
    -0.43
     li
    -0.43
    bra
    -0.43
    POSITIVE LOGITS
    ValueStyle
    0.87
     Wikimedijinoj
    0.81
    styleType
    0.77
     незавершена
    0.73
     ErrIntOverflow
    0.70
    ViewFeatures
    0.70
    thâu
    0.69
    ScopeManager
    0.68
     "..\..\..\
    0.68
    TintMode
    0.67
    Activations Density 0.388%

    No Known Activations