© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 109150
    Prev
    Next
    INDEX
    Explanations

    shrug emoji (ツ)

    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
    '
    1.74
    in
    1.24
    em
    1.20
    ’
    1.20
    ness
    1.11
    at
    1.05
    ed
    1.05
    ang
    1.05
    less
    1.05
    light
    1.00
    POSITIVE LOGITS
    và
    1.23
    ৯
    1.20
    на
    1.12
    ט
    1.11
    나
    1.09
    리
    1.05
    ви
    1.04
    ма
    1.03
    ב
    1.03
    ח
    1.01
    Activations Density 0.000%

    No Known Activations