© 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. 46346
    Prev
    Next
    INDEX
    Explanations

    alpaca, alpex, alara, altra

    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
    К
    0.78
    С
    0.73
    ]#
    0.71
    ה
    0.71
    Се
    0.70
    스
    0.70
    एच
    0.70
     extérieures
    0.70
    אים
    0.69
    ا
    0.66
    POSITIVE LOGITS
    ur
    0.70
    ö
    0.66
    rt
    0.62
    ment
    0.61
     a
    0.60
    ung
    0.60
    p
    0.59
    uh
    0.57
    ymmetry
    0.56
    v
    0.55
    Activations Density 0.005%

    No Known Activations