© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 44027
    Prev
    Next
    INDEX
    Explanations

    Kaitlan Collins, Kaetlyn Osmond, Kai Ito

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ?
    0.87
    א
    0.84
    ه
    0.82
    אן
    0.79
     décidé
    0.79
    স
    0.79
    ት
    0.76
     míst
    0.75
    야
    0.75
    ه‌ای
    0.74
    POSITIVE LOGITS
    to
    0.88
    خ
    0.82
    pas
    0.77
    with
    0.75
     Authorities
    0.71
    𝟬
    0.71
    not
    0.70
    pronged
    0.68
    meh
    0.67
    ver
    0.66
    Activations Density 0.000%

    No Known Activations