© 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. 93328
    Prev
    Next
    INDEX
    Explanations

    multiple choice answers

    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
    ↵↵
    0.59
    ↵
    0.44
     perturbations
    0.41
     которую
    0.40
     управ
    0.40
     приложение
    0.40
     которому
    0.40
    usions
    0.39
    …?
    0.39
     perturbation
    0.39
    POSITIVE LOGITS
     C
    0.68
    C
    0.61
     A
    0.59
    c
    0.56
    **
    0.55
     Following
    0.53
    Furthermore
    0.53
    Therefore
    0.52
     Consequently
    0.52
     **
    0.51
    Activations Density 0.005%

    No Known Activations