© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 50407
    Prev
    Next
    INDEX
    Explanations

    represents

    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_55_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
    érm
    0.38
     symbolized
    0.35
     symbolizing
    0.35
     Ausdruck
    0.35
     प्रेरणा
    0.34
    尊
    0.34
    ерез
    0.34
    ್ಯ
    0.33
     ያ
    0.33
    砕
    0.33
    POSITIVE LOGITS
     rep
    3.94
    Rep
    3.89
     Rep
    3.84
    rep
    3.31
     REP
    2.69
     reps
    2.64
     repr
    2.59
    REP
    2.58
     repell
    2.17
     repellent
    2.16
    Activations Density 0.316%

    No Known Activations