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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 83206
    Prev
    Next
    INDEX
    Explanations

    placeholders like XXXX-XXXX-XXXX-XXXX

    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_0_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
    ;
    1.64
    ?
    1.64
    <0x80>
    1.49
    ه
    1.45
    ០
    1.38
     ০
    1.30
    ),
    1.30
    ᱽ
    1.29
    ۰
    1.27
    !
    1.24
    POSITIVE LOGITS
    를
    1.65
    to
    1.64
    する
    1.55
    و
    1.50
     to
    1.48
    ના
    1.45
    ו
    1.41
     be
    1.38
    g
    1.38
    い
    1.37
    Activations Density 0.000%

    No Known Activations