© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 192255
    Prev
    Next
    INDEX
    Explanations

    recognition, dice, coin, quadratic forms

    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_4_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
     في
    0.71
    1
    0.64
     in
    0.61
    5
    0.59
    Mind
    0.58
     gleich
    0.56
    Token
    0.55
     může
    0.55
    Meyer
    0.55
    াইব
    0.55
    POSITIVE LOGITS
    ید
    0.74
    их
    0.69
    ல்
    0.67
    да
    0.64
    ամ
    0.63
    ने
    0.62
    αν
    0.62
    ک
    0.61
    નુ
    0.60
    να
    0.58
    Activations Density 0.000%

    No Known Activations