© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 198674
    Prev
    Next
    INDEX
    Explanations

    manual, trial, crossed

    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_4_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
    s
    0.22
    es
    0.19
    st
    0.18
    я
    0.17
    p
    0.17
    f
    0.17
    x
    0.16
    g
    0.16
    r
    0.15
    ات
    0.15
    POSITIVE LOGITS
     It
    0.15
    It
    0.13
    Estado
    0.13
     dará
    0.13
    č
    0.13
     کي
    0.12
    Gruß
    0.12
     entró
    0.12
    Über
    0.12
    <unused1049>
    0.12
    Activations Density 0.001%

    No Known Activations