© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 84424
    Prev
    Next
    INDEX
    Explanations

    Spanish 'escríbeme'

    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_0_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
    ای
    1.34
    )
    1.27
    )$,
    1.23
    یم
    1.20
    flavored
    1.19
    owaną
    1.16
    jno
    1.15
    面の
    1.15
    ۹
    1.14
    리의
    1.13
    POSITIVE LOGITS
    м
    2.16
     be
    2.08
    n
    1.97
    و
    1.89
    م
    1.72
    но
    1.70
    at
    1.68
    p
    1.63
    k
    1.61
    не
    1.54
    Activations Density 0.000%

    No Known Activations