© 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. 211355
    Prev
    Next
    INDEX
    Explanations

    parsing code libraries

    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
     சது
    0.43
    médiaire
    0.39
     आरोपों
    0.39
     kammam
    0.38
     ন্যাশনাল
    0.38
    }_{+}
    0.38
     जरिए
    0.38
     favoured
    0.37
     chùa
    0.36
    储
    0.36
    POSITIVE LOGITS
    SEM
    0.50
    繆
    0.42
    ρες
    0.40
     SEM
    0.39
     telescopic
    0.39
    hoc
    0.39
     MEAS
    0.39
    బ్బ
    0.38
    രിക്കുന്ന
    0.38
     instr
    0.38
    Activations Density 0.001%

    No Known Activations