© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 47790
    Prev
    Next
    INDEX
    Explanations

    吉野家, hesitant, attempt, fetish

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_10_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
     tolle
    0.54
    ो
    0.52
     espectacular
    0.51
     junge
    0.51
    ي
    0.50
    য়াস
    0.50
    好的
    0.49
     behav
    0.49
     impressive
    0.49
     좋은
    0.48
    POSITIVE LOGITS
    noon
    0.43
    ci
    0.42
    mi
    0.42
    mias
    0.42
    ma
    0.42
    ilà
    0.41
    जव
    0.41
    whether
    0.40
     c
    0.40
    는
    0.39
    Activations Density 0.000%

    No Known Activations