© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 60216
    Prev
    Next
    INDEX
    Explanations

    pecans ok to eat

    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
    it
    1.88
    ون
    1.87
    u
    1.73
    at
    1.65
    ور
    1.63
    ম
    1.56
    a
    1.55
    as
    1.50
    m
    1.50
    на
    1.48
    POSITIVE LOGITS
     in
    1.21
     are
    1.01
     to
    0.97
    在我们
    0.92
    ák
    0.91
     significant
    0.91
     کہا
    0.90
    NotIn
    0.90
     conductivity
    0.88
    在家
    0.88
    Activations Density 0.000%

    No Known Activations