© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 135033
    Prev
    Next
    INDEX
    Explanations

    honeydew

    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_1_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
     の
    1.10
    。</
    1.05
     as
    1.05
    י
    1.04
    </sub>
    1.02
    т
    1.02
    ί
    0.99
    Ｉ
    0.99
    ៣
    0.99
     in
    0.97
    POSITIVE LOGITS
    '
    1.70
    d
    1.39
    v
    1.35
    h
    1.26
    g
    1.20
    ang
    1.13
    s
    1.12
    ‘
    1.01
    il
    0.97
    ine
    0.95
    Activations Density 0.000%

    No Known Activations