© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 154063
    Prev
    Next
    INDEX
    Explanations

    "></

    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
     لوبه
    0.52
     \%)$
    0.47
     لوبې
    0.45
     âg
    0.44
    拏
    0.44
     NodeJS
    0.43
     gotovo
    0.42
    বহুল
    0.42
    笑顔
    0.41
    ండా
    0.40
    POSITIVE LOGITS
    s
    0.73
    icur
    0.46
    last
    0.46
    str
    0.45
    vari
    0.44
    ss
    0.43
    var
    0.42
    ort
    0.42
    st
    0.42
    rt
    0.42
    Activations Density 0.001%

    No Known Activations