© 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. 231646
    Prev
    Next
    INDEX
    Explanations

    minoxidil

    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
    es
    1.43
    ies
    1.25
    ES
    1.25
    '
    1.16
    ↵↵
    1.13
    ’
    1.12
    ors
    1.09
    us
    1.08
    ers
    1.05
    ions
    1.02
    POSITIVE LOGITS
    ви
    1.15
     його
    1.07
    நபியே
    0.98
     в
    0.97
     projeto
    0.97
     ƙ
    0.94
     distraught
    0.94
     maio
    0.93
    в
    0.91
     pourra
    0.89
    Activations Density 0.000%

    No Known Activations