© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 155540
    Prev
    Next
    INDEX
    Explanations

    say "

    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_60_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
     Sólo
    0.49
    ]\\
    0.49
    :')
    0.48
     También
    0.47
    ）」
    0.47
    )».
    0.46
     Se
    0.46
     Ее
    0.45
    )」
    0.45
     Thing
    0.45
    POSITIVE LOGITS
    ":(
    0.48
    ":
    0.46
    "
    0.45
    mode
    0.45
    `
    0.44
     modify
    0.43
     mode
    0.42
    ,
    0.41
     anthracite
    0.40
     gestion
    0.39
    Activations Density 0.005%

    No Known Activations