© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 85814
    Prev
    Next
    INDEX
    Explanations

    compiler, Bancroft, Lü, Weapon, Hamilton

    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
    ン
    0.84
    н
    0.80
     as
    0.73
    나
    0.71
    া
    0.68
    ce
    0.64
    ला
    0.64
    ര്‍
    0.64
    hz
    0.64
    व
    0.62
    POSITIVE LOGITS
    (
    0.72
    <0x80>
    0.68
    0.63
     i
    0.63
    <0x9A>
    0.62
    <0xA1>
    0.61
    痉
    0.59
     l
    0.59
     tachycardia
    0.59
    '
    0.57
    Activations Density 0.000%

    No Known Activations