© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 30377
    Prev
    Next
    INDEX
    Explanations

    keys and authorization and control

    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_31_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
    向下
    0.40
    TASK
    0.40
    灵
    0.39
    缩
    0.38
     Goddess
    0.38
     pronunciation
    0.36
    pronounced
    0.36
     pronounced
    0.36
     охо
    0.36
    羟
    0.36
    POSITIVE LOGITS
    keys
    0.44
     thresholds
    0.41
    㜌
    0.41
     threshold
    0.41
     alleine
    0.40
     alone
    0.39
     seuls
    0.39
     अकेले
    0.39
     Threshold
    0.39
     allein
    0.38
    Activations Density 0.071%

    No Known Activations