© 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. 61533
    Prev
    Next
    INDEX
    Explanations

    understanding

    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
    would
    0.66
    da
    0.65
     can
    0.64
     is
    0.62
     i
    0.61
     are
    0.59
    can
    0.59
    dept
    0.57
    defer
    0.56
    are
    0.55
    POSITIVE LOGITS
    ב
    0.75
     όμως
    0.71
     connaître
    0.68
     anunciar
    0.66
     ovviamente
    0.66
     لأ
    0.65
     інформа
    0.63
     ομά
    0.63
     België
    0.63
    խ
    0.63
    Activations Density 0.000%

    No Known Activations