© 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. 89197
    Prev
    Next
    INDEX
    Explanations

    visual sexual

    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
    ル
    0.80
    ل
    0.70
    л
    0.61
    ל
    0.56
    ר
    0.52
    尔
    0.50
    р
    0.49
    لل
    0.47
    لما
    0.44
    Pink
    0.44
    POSITIVE LOGITS
    ли
    0.81
    ла
    0.58
    лис
    0.56
    лити
    0.55
    листи
    0.55
    é
    0.55
    ah
    0.52
     liệu
    0.52
    ре
    0.51
    лиза
    0.51
    Activations Density 0.000%

    No Known Activations