© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 205791
    Prev
    Next
    INDEX
    Explanations

    puree

    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
    м
    1.57
    كا
    1.36
    ю
    1.34
    к
    1.28
    ます
    1.27
    ку
    1.22
    يط
    1.20
    лу
    1.20
    كام
    1.16
    ле
    1.10
    POSITIVE LOGITS
    ot
    1.64
    :
    1.62
    i
    1.54
    ari
    1.44
    od
    1.38
    in
    1.36
    ’
    1.35
    ert
    1.34
    ir
    1.30
    int
    1.26
    Activations Density 0.000%

    No Known Activations