© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 236507
    Prev
    Next
    INDEX
    Explanations

    and (followed by noun or verb)

    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_25_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
    ⴽ
    0.37
     ವಿಷ
    0.32
    일상
    0.32
    吘
    0.32
    ವೇ
    0.31
    เข้า
    0.31
    [{}\
    0.31
    Zi
    0.31
    ({\
    0.31
    원이
    0.31
    POSITIVE LOGITS
     fix
    0.37
     arrow
    0.36
     talk
    0.36
     arrows
    0.35
    гом
    0.35
     blind
    0.35
     marcas
    0.34
     whips
    0.34
     ujung
    0.34
     go
    0.33
    Activations Density 0.008%

    No Known Activations