© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 9946
    Prev
    Next
    INDEX
    Explanations

    words related to experiments involving LTD, stimulation, and recording

    oai_token-act-pair · gemini-2.0-flash

    block

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     nahilalakip
    -0.62
     néglig
    -0.60
     uitz
    -0.58
     citoy
    -0.56
     enfans
    -0.56
    endsection
    -0.55
     béné
    -0.55
    спонд
    -0.54
     ['./
    -0.54
    CrossRef
    -0.54
    POSITIVE LOGITS
    $_['
    0.69
    المناصب
    0.60
     TextInputType
    0.54
    TargetException
    0.54
    ponses
    0.53
     disarm
    0.53
     openers
    0.50
    enumii
    0.50
    findpost
    0.50
    Mechanic
    0.50
    Activations Density 5.514%

    No Known Activations