© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 2079
    Prev
    Next
    INDEX
    Explanations

    Fixed

    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_44_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
    Так
    0.34
    Tak
    0.32
    ULTY
    0.31
    Maggie
    0.31
    फरी
    0.30
     পাচ
    0.30
     бір
    0.30
    ᆯ
    0.30
     inputArray
    0.30
     tastefully
    0.29
    POSITIVE LOGITS
    Fixed
    0.40
    fixed
    0.39
     fixed
    0.38
     Fixed
    0.36
    固定
    0.34
     Real
    0.34
     real
    0.33
    real
    0.32
    Real
    0.31
     FIXED
    0.30
    Activations Density 0.000%

    No Known Activations