© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 132843
    Prev
    Next
    INDEX
    Explanations

    perceives situations or things

    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_1_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
     I
    1.27
    н
    1.15
    IN
    1.02
     been
    0.93
    י
    0.90
    ン
    0.90
    ן
    0.88
    }
    0.87
     that
    0.87
     и
    0.84
    POSITIVE LOGITS
    on
    1.30
    ق
    1.28
    h
    1.25
    یا
    1.14
    as
    1.13
    m
    1.07
    ad
    1.06
     as
    1.05
    is
    1.04
    ला
    1.02
    Activations Density 0.000%

    No Known Activations