© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 53811
    Prev
    Next
    INDEX
    Explanations

    time start

    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_31_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
    驱
    0.39
     निकालने
    0.39
    ahun
    0.39
    ಕಾರ
    0.38
     Entertainment
    0.38
     रफ्तार
    0.38
     National
    0.37
     recounts
    0.36
    夫
    0.36
     साल
    0.35
    POSITIVE LOGITS
     delegation
    0.37
    рев
    0.37
     ശി
    0.36
     doo
    0.36
    Deleg
    0.35
    собенно
    0.35
     posebno
    0.35
    朶
    0.34
     деле
    0.34
    மொ
    0.34
    Activations Density 0.004%

    No Known Activations