© 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. 130767
    Prev
    Next
    INDEX
    Explanations

    festinger, felson, nelson

    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
     of
    1.17
     I
    0.99
    通过
    0.98
     It
    0.91
    是
    0.88
    >
    0.87
    [
    0.85
    将
    0.80
    0.79
    స్
    0.78
    POSITIVE LOGITS
    ید
    1.08
    h
    1.06
    f
    1.03
     nightclub
    1.02
    v
    0.99
     جوئے
    0.97
     novia
    0.93
    کسی
    0.93
    の頃
    0.93
     tua
    0.92
    Activations Density 0.002%

    No Known Activations