© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 54303
    Prev
    Next
    INDEX
    Explanations

    URLs and web addresses

    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_31_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
    Marne
    0.27
    DF
    0.27
    楂
    0.26
    vived
    0.26
    DIFF
    0.25
    dif
    0.25
    diff
    0.25
     ধ
    0.25
    ப்ர
    0.25
    probe
    0.24
    POSITIVE LOGITS
     Vä
    0.31
     recepción
    0.27
     Trench
    0.26
     Thin
    0.25
     Fleurit
    0.25
     Tear
    0.25
     koncent
    0.25
     Our
    0.24
     Alz
    0.24
     Ashton
    0.24
    Activations Density 0.003%

    No Known Activations