© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3225
    Prev
    Next
    INDEX
    Explanations

    hyphens and associated words

    oai_token-act-pair · gemini-2.0-flash

    Hyphen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     Efq
    -2.48
     Monfieur
    -2.38
     purpoſe
    -2.31
     myſelf
    -2.28
     pleaſure
    -2.25
     itſelf
    -2.23
     faſt
    -2.22
     ſtate
    -2.17
     raiſ
    -2.16
     Majefty
    -2.16
    POSITIVE LOGITS
     “
    0.93
     
    0.93
    <eos>
    0.90
    ↵↵
    0.89
     de
    0.85
    ↵
    0.85
     (
    0.84
     "
    0.82
     des
    0.80
     en
    0.76
    Activations Density 1.141%

    No Known Activations