© 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. 127274
    Prev
    Next
    INDEX
    Explanations

    dappled sunlight

    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
    ه
    0.91
    a
    0.81
    िंग
    0.79
    ing
    0.77
    л
    0.73
    ה
    0.72
    ة
    0.71
    н
    0.70
    ہ
    0.70
    ма
    0.68
    POSITIVE LOGITS
    B
    0.78
    U
    0.71
    A
    0.71
    }
    0.69
    G
    0.67
    I
    0.66
    C
    0.66
    鋆
    0.66
     e
    0.65
    H
    0.64
    Activations Density 0.000%

    No Known Activations