© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6974
    Prev
    Next
    INDEX
    Explanations

    instances of people caring and doing or not doing based on that, or it could be looking at the past and pondering.

    oai_token-act-pair · gemini-2.0-flash

    the word "so"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     للاسماء
    -0.77
    存于互联网档案馆
    -0.70
    LookAnd
    -0.63
    +#+#
    -0.62
    WriteLiteral
    -0.59
    RequiresApi
    -0.59
    OrNil
    -0.59
    NewUrlParser
    -0.56
    providedIn
    -0.56
    InjectAttribute
    -0.56
    POSITIVE LOGITS
     so
    3.73
    so
    2.70
    So
    2.33
     så
    2.16
     So
    2.14
     così
    2.05
     так
    1.98
     SO
    1.92
    如此
    1.66
     ſo
    1.65
    Activations Density 6.048%

    No Known Activations