© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 43802
    Prev
    Next
    INDEX
    Explanations

    Sam Altman

    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_22_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
     quarters
    0.46
     irrespective
    0.45
     circumfer
    0.44
     threatening
    0.43
     괜
    0.43
     attacks
    0.42
     quadrants
    0.42
     internacionais
    0.42
     watert
    0.41
     sewerage
    0.41
    POSITIVE LOGITS
    耠
    0.45
    Confident
    0.42
    Casual
    0.41
     No
    0.39
    Map
    0.39
    Conf
    0.39
    Result
    0.38
    Projection
    0.37
    Parsing
    0.37
    Compiled
    0.37
    Activations Density 0.000%

    No Known Activations