© 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. 88091
    Prev
    Next
    INDEX
    Explanations

    ga

    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
    ta
    0.58
    gel
    0.56
    tas
    0.55
    m
    0.55
    ting
    0.54
    ga
    0.54
    tel
    0.52
    gers
    0.51
    tipo
    0.50
    ger
    0.49
    POSITIVE LOGITS
    f
    1.08
    is
    0.57
    ه
    0.45
    eV
    0.41
     Entered
    0.41
    ف
    0.41
     fission
    0.41
    fz
    0.40
    eled
    0.40
    fica
    0.40
    Activations Density 0.000%

    No Known Activations