© 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. 91835
    Prev
    Next
    INDEX
    Explanations

    fur

    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
    y
    0.78
    b
    0.54
    yim
    0.49
     so
    0.48
    یان
    0.46
     dedicated
    0.45
     by
    0.42
    yf
    0.41
    yya
    0.41
    yas
    0.40
    POSITIVE LOGITS
    tran
    0.62
    ty
    0.57
    r
    0.55
    trä
    0.54
    tre
    0.54
    tras
    0.54
    trasound
    0.54
    ts
    0.54
    ties
    0.53
    rockets
    0.52
    Activations Density 0.001%

    No Known Activations