© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 207054
    Prev
    Next
    INDEX
    Explanations

    matrices and arrays

    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_56_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
     some
    0.45
     نک
    0.41
     jakiś
    0.40
     []
    0.39
     einige
    0.38
     כמה
    0.38
     alcuni
    0.37
     «
    0.37
     „
    0.37
     qualche
    0.36
    POSITIVE LOGITS
     BOB
    0.42
    坻
    0.39
    ⒈
    0.38
    Lucy
    0.38
    هَا
    0.36
    썰
    0.36
    ▔
    0.36
     మారింది
    0.36
     следующее
    0.36
    тию
    0.36
    Activations Density 0.002%

    No Known Activations