© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 81925
    Prev
    Next
    INDEX
    Explanations

    AI model introductions

    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_53_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
     ...
    0.44
     -
    0.41
    XYZ
    0.40
    ---
    0.40
    act
    0.39
    xyz
    0.38
    “
    0.37
    iterator
    0.36
    TYPE
    0.36
    owanie
    0.36
    POSITIVE LOGITS
    శ్వ
    0.45
    Ҥ
    0.43
    <unused654>
    0.43
    <unused33>
    0.42
    <unused714>
    0.41
     TestAvg
    0.40
     thisStudent
    0.40
     theyre
    0.40
    <unused1073>
    0.39
    gettags
    0.39
    Activations Density 0.038%

    No Known Activations