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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 203331
    Prev
    Next
    INDEX
    Explanations

    that offers

    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_6_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
    خ
    0.93
    ј
    0.88
    ם
    0.87
     calent
    0.86
    niejszych
    0.84
    ьте
    0.82
    نی
    0.82
    كون
    0.81
    вую
    0.81
    ων
    0.81
    POSITIVE LOGITS
    a
    1.42
    t
    1.31
    r
    1.30
    em
    1.14
    l
    1.08
    n
    1.06
    et
    1.02
    g
    1.02
    d
    0.97
    f
    0.93
    Activations Density 0.007%

    No Known Activations