© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 143055
    Prev
    Next
    INDEX
    Explanations

    methods

    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_46_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
    wpilib
    0.38
    য়ন
    0.37
    herst
    0.37
    ongi
    0.36
     п
    0.35
     COMPENSATION
    0.35
     uint
    0.35
    勤
    0.34
    ｜
    0.34
    gevens
    0.34
    POSITIVE LOGITS
     methods
    1.52
     Methods
    1.52
    methods
    1.49
    Methods
    1.45
     métodos
    1.38
     методы
    1.34
     методов
    1.32
     Methoden
    1.29
     METHODS
    1.28
     méthodes
    1.25
    Activations Density 0.000%

    No Known Activations