© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 39540
    Prev
    Next
    INDEX
    Explanations

    Den

    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_57_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
    ATES
    0.41
    ಥ
    0.38
    atios
    0.38
     महम
    0.38
    ahassee
    0.37
     MARINE
    0.37
    ეთის
    0.36
    panelMenuList
    0.36
    হ
    0.36
    FIELD
    0.35
    POSITIVE LOGITS
    xima
    0.41
    alda
    0.39
    erai
    0.38
    लान
    0.37
    ер
    0.36
    mbr
    0.36
    sic
    0.35
     zwart
    0.35
    i
    0.35
    ear
    0.35
    Activations Density 0.000%

    No Known Activations