© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 161205
    Prev
    Next
    INDEX
    Explanations

    photoreceptor, photocopy, anarchist

    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
    い
    1.56
    ς
    1.10
    ний
    1.06
    에요
    1.04
    야
    0.96
    itaan
    0.93
    aj
    0.92
     aritmética
    0.90
    라고
    0.89
    foot
    0.88
    POSITIVE LOGITS
    ہ
    1.91
    to
    1.86
    و
    1.82
    the
    1.78
    ب
    1.62
    ج
    1.56
    >
    1.48
    이었
    1.45
    은
    1.43
    ع
    1.41
    Activations Density 0.001%

    No Known Activations