© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1802
    Prev
    Next
    INDEX
    Explanations

    sum

    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_39_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
    Usage
    0.39
    CopyWith
    0.38
    ilaire
    0.38
    गली
    0.37
    ㄕ
    0.37
     Gabb
    0.37
     Usage
    0.37
    コピー
    0.37
    ಹಾಸ
    0.37
    ቭ
    0.37
    POSITIVE LOGITS
     sum
    0.42
     half
    0.42
     SUM
    0.41
     eros
    0.40
     lut
    0.40
    isf
    0.39
    azir
    0.39
     scrim
    0.38
     ero
    0.38
    artic
    0.37
    Activations Density 0.008%

    No Known Activations