© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 221067
    Prev
    Next
    INDEX
    Explanations

    blind spots

    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_10_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
    ों
    0.92
    м
    0.74
    es
    0.71
    s
    0.68
    ले
    0.67
    ल
    0.64
    л
    0.63
    le
    0.63
    ле
    0.62
    م
    0.59
    POSITIVE LOGITS
     universitaria
    0.60
     conexión
    0.60
    už
    0.60
    t
    0.60
     Eylül
    0.59
    שׁ
    0.59
     instalación
    0.59
    هِ
    0.59
     යන
    0.59
     murah
    0.58
    Activations Density 0.000%

    No Known Activations