© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 31561
    Prev
    Next
    INDEX
    Explanations

    sunrise and sunset light

    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_31_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
    ෘ
    0.30
    受賞
    0.29
    毛
    0.28
    forecast
    0.27
    ڊ
    0.27
    querySelector
    0.27
    instruments
    0.27
    vas
    0.26
    preview
    0.26
    voucher
    0.26
    POSITIVE LOGITS
    Ctr
    0.35
    ቛ
    0.34
     दंग
    0.33
     detonations
    0.33
    }})$
    0.31
    ATPase
    0.31
     विरा
    0.31
     हिंसा
    0.30
     Midway
    0.30
     मिड
    0.30
    Activations Density 0.024%

    No Known Activations