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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 10481
    Prev
    Next
    INDEX
    Explanations

    `+` or `__all__` followed by list items

    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_40_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
     гле
    0.40
    হাওয়া
    0.38
    溸
    0.34
    geocode
    0.34
     FileWriter
    0.34
     Kayla
    0.34
     Compu
    0.34
     Searle
    0.34
    ែ
    0.33
    antial
    0.33
    POSITIVE LOGITS
     +
    0.49
    +(
    0.44
    +
    0.41
     F
    0.39
    ]+
    0.38
    ']+
    0.37
     nesse
    0.37
    +{\
    0.36
     +=
    0.35
     +(
    0.35
    Activations Density 0.000%

    No Known Activations