© 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. 143242
    Prev
    Next
    INDEX
    Explanations

    questioning sanity or writing letters

    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
    ون
    0.84
    ции
    0.75
    姆
    0.72
    த்தில்
    0.69
    væ
    0.69
     ocasi
    0.69
    .³
    0.68
    .??.??"]
    0.68
    ونم
    0.68
    вата
    0.67
    POSITIVE LOGITS
    n
    1.13
    {
    0.86
    is
    0.75
    en
    0.73
    an
    0.69
    ли
    0.69
    nY
    0.68
     depolar
    0.65
    start
    0.64
    は
    0.64
    Activations Density 0.000%

    No Known Activations