© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 67405
    Prev
    Next
    INDEX
    Explanations

    thoughtfully

    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_51_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
    óstico
    0.43
     কাল
    0.40
    꽁
    0.39
    దాయ
    0.39
     Kimberly
    0.39
     eric
    0.39
     Juliet
    0.38
     divalent
    0.37
    帘
    0.37
     Lori
    0.37
    POSITIVE LOGITS
     पवार
    0.44
    Ow
    0.40
    Gw
    0.39
    ową
    0.38
     Năm
    0.38
    сайт
    0.37
    МІ
    0.37
     Gw
    0.37
    bhp
    0.37
    tw
    0.36
    Activations Density 0.009%

    No Known Activations