© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 39146
    Prev
    Next
    INDEX
    Explanations

    Pobyt, Pop, pobudzać, поболтать

    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_3_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
    ’
    1.30
    وم
    0.85
    ‘
    0.84
    ”
    0.79
    '
    0.76
    ի
    0.75
    ée
    0.74
    िको
    0.74
    ag
    0.72
    υ
    0.72
    POSITIVE LOGITS
    ق
    0.76
    ر
    0.72
    র
    0.68
    тся
    0.65
    する
    0.64
    ts
    0.63
     tyrannical
    0.61
    फारिश
    0.61
    স
    0.61
    ש
    0.61
    Activations Density 0.000%

    No Known Activations