© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 112643
    Prev
    Next
    INDEX
    Explanations

    APK (Android Package Kit)

    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_2_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
    ли
    1.17
    ر
    1.09
    ur
    1.02
    تان
    0.89
    у
    0.88
    로
    0.88
     стали
    0.88
    عين
    0.84
    し
    0.83
    <unused37>
    0.81
    POSITIVE LOGITS
    a
    1.44
     a
    1.28
    า
    1.25
    나
    1.14
    리
    1.13
    of
    1.12
    های
    1.12
    या
    1.09
    ों
    1.09
    ances
    1.09
    Activations Density 0.000%

    No Known Activations