© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 247261
    Prev
    Next
    INDEX
    Explanations

    privacy legislation

    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_40_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
    isor
    0.39
    백
    0.36
    propylene
    0.36
    classe
    0.35
     پڑ
    0.34
    NaHCO
    0.34
    packageName
    0.34
     Pab
    0.34
    ቿ
    0.34
    Dimethyl
    0.34
    POSITIVE LOGITS
    ポイント
    0.47
     points
    0.41
     लिखते
    0.41
     photo
    0.40
    씀
    0.40
     performance
    0.39
     miss
    0.39
     writing
    0.39
    Model
    0.39
     moves
    0.39
    Activations Density 0.000%

    No Known Activations