© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 142411
    Prev
    Next
    INDEX
    Explanations

    the reason

    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_12_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    },
    0.63
    ana
    0.61
    ons
    0.60
    ని
    0.59
    Ph
    0.58
    Phot
    0.56
    fromJson
    0.56
    activity
    0.55
    ના
    0.54
    Roboto
    0.54
    POSITIVE LOGITS
     тысячи
    0.56
     audits
    0.55
     crimin
    0.55
     individus
    0.55
     mūsų
    0.54
     т
    0.54
     categor
    0.54
    িনবার্গ
    0.54
     silicon
    0.54
     میزان
    0.53
    Activations Density 0.000%

    No Known Activations