© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 199101
    Prev
    Next
    INDEX
    Explanations

    self. method definition

    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_27_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
     팀
    0.37
    لاسه
    0.36
     rearrange
    0.35
     ليا
    0.35
     restructure
    0.35
    Ма
    0.34
    ंक्शन
    0.34
     rearrangement
    0.33
    팀
    0.33
    अन
    0.33
    POSITIVE LOGITS
     evidente
    0.45
     documento
    0.42
     einmal
    0.41
    icularly
    0.40
     जादू
    0.40
    yna
    0.39
    幵
    0.39
     oportunidad
    0.39
    жах
    0.39
     segunda
    0.38
    Activations Density 0.000%

    No Known Activations