© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 174795
    Prev
    Next
    INDEX
    Explanations

    dev

    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_24_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
    Joining
    0.39
     omnichannel
    0.39
     omn
    0.39
    യ
    0.38
    कि
    0.38
    อย่าง
    0.38
    贏
    0.38
    ال
    0.37
     Bra
    0.37
    เน
    0.37
    POSITIVE LOGITS
     BGPS
    0.43
     glycerol
    0.43
     hObject
    0.43
    mpeg
    0.41
    blichen
    0.41
    bj
    0.41
    attoo
    0.40
     popOperand
    0.39
     كلمه
    0.39
    apshot
    0.39
    Activations Density 0.000%

    No Known Activations