© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 203814
    Prev
    Next
    INDEX
    Explanations

    whenever

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     need
    0.44
    usnya
    0.43
    need
    0.42
     Might
    0.42
     teie
    0.42
     Need
    0.41
     Worse
    0.40
     Presently
    0.40
    Muy
    0.38
    ٸ
    0.38
    POSITIVE LOGITS
     पुरालेखित
    0.42
     ระบบ
    0.37
    :.
    0.35
     ():
    0.35
     opportunità
    0.34
     দিবার
    0.33
    触
    0.33
     ().
    0.33
     currentChar
    0.33
     ESTATE
    0.33
    Activations Density 0.001%

    No Known Activations