© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 107630
    Prev
    Next
    INDEX
    Explanations

    town

    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_1_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
    ный
    1.21
    ре
    1.13
    с
    1.08
    ного
    1.03
    न्
    1.02
    vironment
    1.01
     (
    0.98
    ك
    0.97
    ных
    0.97
    ве
    0.96
    POSITIVE LOGITS
    ي
    0.99
    যোগ্য
    0.97
    ONE
    0.96
    行った
    0.95
    ال
    0.93
    적인
    0.93
    BA
    0.92
    行う
    0.91
    이니까
    0.91
     slashed
    0.89
    Activations Density 0.000%

    No Known Activations