© 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. 89112
    Prev
    Next
    INDEX
    Explanations

    sp

    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
    reas
    0.38
     turned
    0.37
     necessità
    0.36
    റ
    0.36
     gestire
    0.35
    ø
    0.35
     reimbursed
    0.35
     Attacks
    0.35
    琐
    0.35
     shrugged
    0.34
    POSITIVE LOGITS
    ider
    1.41
    IDER
    0.89
    ებულია
    0.45
    istent
    0.43
    istency
    0.42
    ULT
    0.42
    ision
    0.42
     happen
    0.41
     කරන
    0.40
    駿
    0.39
    Activations Density 0.002%

    No Known Activations