© 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. 48269
    Prev
    Next
    INDEX
    Explanations

    list indices or matrix access

    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
    Not in Any Lists

    No Comments

    Negative Logits
     adenovirus
    0.38
     Kamen
    0.36
    zze
    0.35
     chew
    0.35
    髑
    0.34
     million
    0.34
     synt
    0.33
     intrat
    0.33
    蝙
    0.33
    chema
    0.33
    POSITIVE LOGITS
    ைகிறது
    0.39
    Continuing
    0.38
    ]}/${
    0.38
    deviceName
    0.38
     دوبارہ
    0.37
     பாதுகாக்க
    0.36
    PROTE
    0.36
    drawLine
    0.36
     persiapan
    0.36
     його
    0.36
    Activations Density 0.002%

    No Known Activations