© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 240430
    Prev
    Next
    INDEX
    Explanations

    importance of

    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_25_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
     normalize
    0.37
    |_
    0.36
    生成
    0.35
     normalized
    0.35
    该
    0.35
     Generations
    0.35
     mice
    0.35
     annot
    0.35
     BERN
    0.35
     正
    0.34
    POSITIVE LOGITS
    ്ര
    0.44
     sekund
    0.41
     Barriers
    0.41
     بالأ
    0.40
    ോടെ
    0.40
     pręd
    0.40
     králov
    0.40
    beelding
    0.39
     perchè
    0.39
    htaking
    0.39
    Activations Density 0.001%

    No Known Activations