© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 3107
    Prev
    Next
    INDEX
    Explanations

    assigning string value

    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_39_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
     up
    0.19
    ----
    0.18
    0.17
    e
    0.17
    <i>
    0.17
     Stan
    0.17
    -
    0.17
    6
    0.17
    as
    0.16
     driven
    0.16
    POSITIVE LOGITS
     haught
    0.21
    蠱
    0.20
     trout
    0.20
     tweed
    0.20
     sumptuous
    0.19
     luscious
    0.19
     huts
    0.19
     degr
    0.19
     علیحد
    0.19
    ជី
    0.18
    Activations Density 0.197%

    No Known Activations