© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 205891
    Prev
    Next
    INDEX
    Explanations

    adjusting microphone

    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_37_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
     Donor
    0.42
     Ory
    0.42
    参
    0.40
     yen
    0.39
    Donor
    0.39
    donor
    0.38
     लोकसभा
    0.38
     डिप्ट
    0.38
     donor
    0.37
    दूसरे
    0.37
    POSITIVE LOGITS
     shirt
    1.27
     clothing
    1.19
     shirts
    1.17
     لباس
    1.14
     shoes
    1.13
    เสื้อ
    1.11
     clothes
    1.09
     옷
    1.09
    shirt
    1.08
    衣服
    1.08
    Activations Density 0.053%

    No Known Activations