© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 261431
    Prev
    Next
    INDEX
    Explanations

    Dunning

    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_5_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
     lungo
    1.37
     σε
    1.34
     в
    1.32
     mediante
    1.31
     compañ
    1.22
    ում
    1.21
     dù
    1.21
    ți
    1.20
     nuestra
    1.20
     penchant
    1.17
    POSITIVE LOGITS
    s
    2.44
    1
    2.09
    the
    1.97
    ll
    1.90
    j
    1.89
    ف
    1.84
    to
    1.80
    li
    1.77
    de
    1.72
    se
    1.71
    Activations Density 0.000%

    No Known Activations