© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 108396
    Prev
    Next
    INDEX
    Explanations

    plakortolides

    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_1_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
    ↵
    1.48
    an
    1.44
    ור
    1.18
    ী
    1.12
    ar
    1.02
     ”
    0.94
    मा
    0.94
    ാ
    0.93
    ো
    0.92
     American
    0.91
    POSITIVE LOGITS
    Z
    1.15
    I
    1.14
    С
    1.14
     sesión
    1.04
     susc
    1.02
     сосредото
    1.01
    ó
    1.00
    К
    0.99
    ábado
    0.98
    ll
    0.98
    Activations Density 0.001%

    No Known Activations