© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 175407
    Prev
    Next
    INDEX
    Explanations

    methods for analysis

    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_20_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
    wikipedia
    0.47
    oulton
    0.43
    '/
    0.43
     محک
    0.43
    nltk
    0.42
    پاکستان
    0.42
     каждое
    0.41
    🚴
    0.41
    '})
    0.40
    আন
    0.40
    POSITIVE LOGITS
     paralysis
    0.45
     मित्त
    0.43
     ident
    0.42
     SV
    0.42
     imaging
    0.42
     KV
    0.42
     зна
    0.41
     degeneracy
    0.41
     Imaging
    0.41
     Avatar
    0.41
    Activations Density 0.005%

    No Known Activations