© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 195255
    Prev
    Next
    INDEX
    Explanations

    speak Japanese?

    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_4_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
    ции
    1.05
    ない
    0.86
    㓶
    0.85
    는데
    0.83
    켰
    0.82
    였
    0.81
    偐
    0.80
    려면
    0.79
    症状
    0.78
    ция
    0.75
    POSITIVE LOGITS
    and
    1.52
    in
    1.33
    ig
    1.29
    "
    1.20
    i
    1.20
    '
    1.18
    an
    1.17
    ח
    1.09
    at
    1.08
    et
    1.06
    Activations Density 0.000%

    No Known Activations