© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 23924
    Prev
    Next
    INDEX
    Explanations

    separate

    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_56_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
     ग्
    0.37
     sri
    0.37
     x
    0.36
    centaje
    0.36
     thing
    0.36
     ১ম
    0.36
     باتیں
    0.36
     इ
    0.36
     ersten
    0.35
    ینہ
    0.35
    POSITIVE LOGITS
     Separate
    0.98
     separate
    0.89
    Separate
    0.86
    separate
    0.86
     seperate
    0.73
     আলাদা
    0.65
    別
    0.62
     separ
    0.57
     ayrı
    0.57
     отдельно
    0.57
    Activations Density 0.018%

    No Known Activations