© 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. 132960
    Prev
    Next
    INDEX
    Explanations

    etcetera

    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
    ुस्तान
    1.06
    ни
    1.05
    mental
    1.04
    er
    1.03
    lund
    1.02
    ありました
    1.02
    телни
    0.99
    }$)
    0.99
     proteção
    0.98
    Were
    0.97
    POSITIVE LOGITS
     on
    1.59
     is
    1.45
     has
    1.42
    મ
    1.39
    ח
    1.30
    ש
    1.24
    מ
    1.20
     to
    1.19
     $
    1.18
    IS
    1.18
    Activations Density 0.000%

    No Known Activations