© 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. 126838
    Prev
    Next
    INDEX
    Explanations

    around ideas or random movement

    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
    2
    0.74
    J
    0.70
    ید
    0.68
    S
    0.64
    L
    0.64
    Day
    0.63
    V
    0.62
    F
    0.61
    ách
    0.60
    A
    0.60
    POSITIVE LOGITS
    on
    0.91
    ों
    0.85
    ের
    0.83
    ים
    0.82
    s
    0.82
    ol
    0.81
    in
    0.79
    sı
    0.77
    та
    0.77
    k
    0.76
    Activations Density 0.000%

    No Known Activations