© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 7378
    Prev
    Next
    INDEX
    Explanations

    model

    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
     m
    0.37
     resent
    0.37
    HUN
    0.37
    osti
    0.37
     Synd
    0.37
     character
    0.36
     flattening
    0.36
     î
    0.36
    }`,
    0.36
     tus
    0.35
    POSITIVE LOGITS
    Support
    0.42
    Fact
    0.42
    golden
    0.42
     Support
    0.41
     Sko
    0.41
     Fact
    0.38
    Analysis
    0.38
    Baca
    0.37
    Golden
    0.37
    Splash
    0.37
    Activations Density 0.024%

    No Known Activations