© 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. 86849
    Prev
    Next
    INDEX
    Explanations

    acogedor

    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
    u
    1.25
    us
    0.93
    im
    0.89
    ad
    0.81
    ug
    0.77
    uq
    0.75
    é
    0.75
    ua
    0.72
    w
    0.70
    is
    0.69
    POSITIVE LOGITS
    ال
    1.20
    یل
    0.91
    み
    0.82
    一
    0.79
    ก
    0.77
    いますが
    0.74
    一丝
    0.74
    데
    0.73
    اک
    0.73
    ת
    0.71
    Activations Density 0.002%

    No Known Activations