© 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. 92036
    Prev
    Next
    INDEX
    Explanations

    json

    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
    ofType
    0.48
    rings
    0.46
    into
    0.46
    ⬥
    0.46
    ating
    0.45
    ik
    0.44
    acij
    0.43
    was
    0.42
    ning
    0.42
    were
    0.42
    POSITIVE LOGITS
     static
    0.36
     Meeting
    0.35
     ‘
    0.34
     nodding
    0.34
    ’
    0.34
     meeting
    0.33
     soud
    0.33
     arrêt
    0.33
    ாயம்
    0.33
     incluso
    0.33
    Activations Density 0.001%

    No Known Activations