© 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. 3264
    Prev
    Next
    INDEX
    Explanations

    words related to interacting on a chat server

    oai_token-act-pair · gemini-2.0-flash

    sur

    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
     auroit
    -0.98
     avoient
    -0.98
     étoient
    -0.93
     feroit
    -0.93
     pouvoit
    -0.88
     étoit
    -0.87
     prêtres
    -0.85
     temporaire
    -0.84
     Hongrie
    -0.83
     Romains
    -0.82
    POSITIVE LOGITS
    ↵
    0.59
     defaultstate
    0.59
    ↵↵
    0.48
     whereas
    0.47
     invol
    0.47
    بوابة
    0.46
    on
    0.46
    memcpy
    0.46
    водство
    0.45
     concom
    0.45
    Activations Density 0.340%

    No Known Activations