© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 39935
    Prev
    Next
    INDEX
    Explanations

    class lp

    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_11_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
    ابی
    0.17
     தொடர்பு
    0.17
     conflicto
    0.17
     jord
    0.16
    誣
    0.15
     contenedor
    0.15
    ]]);
    0.15
     همه
    0.15
    もちろん
    0.15
     fuerte
    0.15
    POSITIVE LOGITS
    t
    0.23
    s
    0.22
    in
    0.20
     at
    0.20
    towards
    0.19
    r
    0.19
     begins
    0.18
    m
    0.18
     Czę
    0.17
     breezes
    0.17
    Activations Density 0.006%

    No Known Activations