© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 37819
    Prev
    Next
    INDEX
    Explanations

    Technical information parsing

    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_57_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
    避け
    0.38
     daytime
    0.38
     Daylight
    0.38
    妣
    0.38
     Mell
    0.37
    अली
    0.36
     Ausbildung
    0.36
     maim
    0.36
     deth
    0.36
     tuj
    0.36
    POSITIVE LOGITS
    鿷
    0.37
    <?=
    0.36
    জয়
    0.34
    ுகிற
    0.34
    Connecticut
    0.34
     позволи
    0.33
    period
    0.32
    されます
    0.32
    valueOf
    0.32
    Unlock
    0.32
    Activations Density 0.007%

    No Known Activations