© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 36141
    Prev
    Next
    INDEX
    Explanations

    colander helmet

    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
    at
    0.81
    री
    0.64
    is
    0.63
    m
    0.62
    يد
    0.61
    𝘢
    0.60
    un
    0.59
    ed
    0.59
    тел
    0.59
    <0x0D>
    0.58
    POSITIVE LOGITS
    ’
    0.86
    -
    0.80
     atk
    0.80
    &=
    0.74
    釟
    0.71
     істо
    0.70
    :=
    0.67
     Besançon
    0.65
     выбо
    0.64
    =
    0.62
    Activations Density 0.001%

    No Known Activations