© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 61837
    Prev
    Next
    INDEX
    Explanations

    reason about

    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_11_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
    р
    0.65
    etos
    0.54
    FAPI
    0.54
    P
    0.51
    াফ
    0.51
    Else
    0.51
    walker
    0.50
    H
    0.50
    淀
    0.50
    ться
    0.50
    POSITIVE LOGITS
     druhé
    0.59
     Người
    0.59
     použ
    0.59
     supérieure
    0.56
     Últ
    0.56
     Jac
    0.55
     pouvez
    0.54
     إلى
    0.54
    ñ
    0.54
     só
    0.52
    Activations Density 0.020%

    No Known Activations