© 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. 39244
    Prev
    Next
    INDEX
    Explanations

    hard rock

    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
    리
    0.71
    bahan
    0.67
    hiddenMap
    0.67
    setzen
    0.64
    FileInputExcel
    0.63
    ৬
    0.61
    ভাগের
    0.60
    ৯
    0.60
    "{@
    0.59
    níci
    0.59
    POSITIVE LOGITS
     a
    0.86
    er
    0.82
    ו
    0.80
            
    0.74
    ↵
    0.73
     l
    0.73
     by
    0.73
    a
    0.73
     showers
    0.72
    o
    0.71
    Activations Density 0.001%

    No Known Activations