© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 123178
    Prev
    Next
    INDEX
    Explanations

    vb.net code

    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_3_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
     (
    0.64
    ५
    0.59
    st
    0.57
    don
    0.54
    ٥
    0.54
     in
    0.53
    did
    0.52
    esse
    0.51
    infile
    0.50
    versions
    0.50
    POSITIVE LOGITS
    ра
    0.84
    ’
    0.80
    وی
    0.80
    ہ
    0.79
    𝓶
    0.76
    ми
    0.71
    یک
    0.71
    ب
    0.71
    াস
    0.71
    र
    0.71
    Activations Density 0.001%

    No Known Activations