© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 81713
    Prev
    Next
    INDEX
    Explanations

    triggers or racking

    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_0_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
     on
    1.90
    ad
    1.41
     be
    1.33
    ung
    1.32
     a
    1.25
    ز
    1.25
     )
    1.23
    する
    1.20
    ↵
    1.16
     }
    1.16
    POSITIVE LOGITS
    ни
    1.68
    ри
    1.27
    с
    1.17
    тем
    1.15
    inė
    1.11
    ро
    1.09
    тва
    1.09
     thermocouple
    1.09
    hitva
    1.09
    ה
    1.09
    Activations Density 0.001%

    No Known Activations