© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 90246
    Prev
    Next
    INDEX
    Explanations

    Sw

    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_60_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
    ინა
    0.42
     Throw
    0.41
    蓁
    0.40
     Mér
    0.39
     ม
    0.37
     हेव
    0.36
     Villan
    0.36
    лове
    0.35
     vzt
    0.35
     Մ
    0.35
    POSITIVE LOGITS
    mr
    0.48
    rfc
    0.45
    nx
    0.45
    any
    0.42
    ^*
    0.41
    nc
    0.40
    nr
    0.39
    ns
    0.39
    aj
    0.38
    ami
    0.38
    Activations Density 0.000%

    No Known Activations