© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 134745
    Prev
    Next
    INDEX
    Explanations

    cost of sacrifice

    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_6_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
    DE
    0.94
    IM
    0.93
    ha
    0.90
    '
    0.89
    LE
    0.89
    p
    0.89
    ADA
    0.88
    AK
    0.86
    ONE
    0.86
    IL
    0.86
    POSITIVE LOGITS
    सँग
    0.88
    odigd
    0.85
    賏
    0.83
    㕶
    0.80
    atief
    0.80
    絫
    0.79
    洏
    0.77
    يّ
    0.76
    ához
    0.75
    گي
    0.75
    Activations Density 0.000%

    No Known Activations