© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 48392
    Prev
    Next
    INDEX
    Explanations

    Intake, Primarily, Lah, Typically, Massive, Very

    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_31_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
     –
    0.25
    —
    0.24
     Admiral
    0.23
     -
    0.23
     Unlike
    0.22
     Details
    0.22
    秉
    0.22
     ArrayList
    0.21
    unlike
    0.21
    ほど
    0.21
    POSITIVE LOGITS
    ạc
    0.25
     potentiel
    0.24
    ᓐ
    0.24
     いう
    0.23
    諏
    0.23
    frac
    0.23
    βά
    0.23
     اوس
    0.23
    ையை
    0.22
    ಶ
    0.22
    Activations Density 0.055%

    No Known Activations