© 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. 2999
    Prev
    Next
    INDEX
    Explanations

    the word "point" followed by a dash or the words "in" or "to"

    oai_token-act-pair · gemini-2.0-flash

    point

    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
    Negative Logits
     betweenstory
    -0.78
    RegressionTest
    -0.56
    entile
    -0.53
    èle
    -0.50
    DEN
    -0.49
    setopt
    -0.49
     aVar
    -0.49
    Fine
    -0.48
     enf
    -0.48
     gondola
    -0.48
    POSITIVE LOGITS
    //
    0.72
    mybatisplus
    0.63
     @"/
    0.59
    rophes
    0.57
    rungsseite
    0.57
    matchCondition
    0.57
    enheim
    0.57
    Legături
    0.56
    zzar
    0.55
    RectangleBorder
    0.54
    Activations Density 6.591%

    No Known Activations