© 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. 247258
    Prev
    Next
    INDEX
    Explanations

    return statements

    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
     exponencial
    0.34
    ០០
    0.34
     ανθρώ
    0.33
    ারে
    0.33
    洄
    0.32
    阱
    0.32
    姮
    0.32
     ocul
    0.32
     तट
    0.31
     laguna
    0.31
    POSITIVE LOGITS
     mountain
    0.34
     Gottlieb
    0.32
    ishes
    0.32
     si
    0.31
    .`
    0.31
     buck
    0.30
     SI
    0.30
     Smith
    0.29
     champion
    0.29
     ·
    0.29
    Activations Density 0.001%

    No Known Activations