© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 79899
    Prev
    Next
    INDEX
    Explanations

    pear

    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_0_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
    ל
    1.63
    ल
    1.50
    ت
    1.36
    ک
    1.25
    ᱗
    1.24
    ク
    1.20
    荇
    1.19
    ল
    1.17
    ુ
    1.17
    ס
    1.16
    POSITIVE LOGITS
    S
    1.85
    T
    1.84
    R
    1.81
    ’
    1.70
    D
    1.64
    P
    1.61
    L
    1.59
    G
    1.52
    B
    1.46
    K
    1.45
    Activations Density 0.001%

    No Known Activations