© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 169765
    Prev
    Next
    INDEX
    Explanations

    manic

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    ist
    0.40
    été
    0.38
    following
    0.38
     følgende
    0.38
     following
    0.37
    M
    0.37
    aspect
    0.36
    qty
    0.36
    extreme
    0.36
    occa
    0.35
    POSITIVE LOGITS
    ራዊ
    0.43
    ures
    0.43
    URES
    0.42
    సుకొ
    0.41
    嘀
    0.41
     cirk
    0.40
    URE
    0.40
    ûr
    0.39
    xRt
    0.39
    యు
    0.38
    Activations Density 0.000%

    No Known Activations