© 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. 103147
    Prev
    Next
    INDEX
    Explanations

    lunar or ö-prefix words

    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
    8
    1.52
    5
    1.39
    ES
    1.22
    6
    1.18
    ANG
    1.17
    .
    1.17
    4
    1.14
    es
    1.09
    ING
    1.09
    ↵
    1.08
    POSITIVE LOGITS
    a
    1.30
    ма
    1.09
    вається
    0.98
    ن
    0.96
    มัน
    0.95
    مود
    0.94
    یم
    0.93
    ъем
    0.93
    க்கு
    0.92
    说过
    0.92
    Activations Density 0.000%

    No Known Activations