© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10083
    Prev
    Next
    INDEX
    Explanations

    numerical data, sometimes including surrounding punctuation and related symbols such as "%," "-", and ".".

    oai_token-act-pair · gemini-2.0-flash

    Numerical and prime factor data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     gynhyrchwyd
    -0.74
     autorytatywna
    -0.68
    IUrlHelper
    -0.66
    Hochspringen
    -0.64
     سكانية
    -0.63
    enderror
    -0.63
     BaseModel
    -0.58
     Jefus
    -0.56
     plastiques
    -0.56
     occaf
    -0.55
    POSITIVE LOGITS
    InjectAttribute
    0.64
     Roskov
    0.58
    دانشنامهٔ
    0.52
     two
    0.48
     Six
    0.48
    Билгалдахарш
    0.47
    帖最后由
    0.46
    ContentAlignment
    0.46
    ISupport
    0.46
     Two
    0.46
    Activations Density 1.834%

    No Known Activations