© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 53350
    Prev
    Next
    INDEX
    Explanations

    special characters

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_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
     Das
    0.44
    esu
    0.44
    Das
    0.41
    ﺼ
    0.41
    das
    0.39
     Pasta
    0.39
     volume
    0.39
     Hope
    0.38
     volumes
    0.38
    perate
    0.38
    POSITIVE LOGITS
    ĕ
    0.88
    ě
    0.78
    ěn
    0.73
    ӗ
    0.69
    ět
    0.65
    ění
    0.65
    Ě
    0.65
    ěné
    0.63
    ë
    0.63
    Ĕ
    0.62
    Activations Density 0.000%

    No Known Activations