© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 168245
    Prev
    Next
    INDEX
    Explanations

    saving time

    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_34_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
    時間の
    0.45
     Schnell
    0.44
     kans
    0.40
     hours
    0.39
    時間を
    0.39
     시간을
    0.39
     spend
    0.36
    㹮
    0.36
    ấn
    0.36
     времени
    0.35
    POSITIVE LOGITS
     փ
    0.42
     prepara
    0.41
     prepar
    0.40
    籌
    0.40
    required
    0.40
    Prepar
    0.40
    Salve
    0.38
    括号
    0.38
     дво
    0.37
     GRAM
    0.37
    Activations Density 0.003%

    No Known Activations