© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 199807
    Prev
    Next
    INDEX
    Explanations

    no concept of

    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_12_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
     reino
    0.72
     knew
    0.70
     desconocido
    0.68
     bambino
    0.65
     tenido
    0.65
     n
    0.63
    知道
    0.61
     conocer
    0.60
     llegada
    0.60
     from
    0.59
    POSITIVE LOGITS
    ^-
    0.57
    NCc
    0.54
     لأنه
    0.52
    қы
    0.52
    because
    0.52
    geist
    0.51
    щего
    0.51
    !-
    0.50
     ಸರ
    0.50
    ချုပ်
    0.50
    Activations Density 0.000%

    No Known Activations