© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 202785
    Prev
    Next
    INDEX
    Explanations

    bot command prefix

    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_37_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
    cog
    0.40
    靥
    0.40
     विपक्षी
    0.38
    luc
    0.37
    রাম
    0.37
     சிறிய
    0.37
    ையான
    0.36
    Cog
    0.36
    락
    0.36
     hacked
    0.36
    POSITIVE LOGITS
    true
    0.40
     discont
    0.39
    ジタル
    0.39
     true
    0.37
    novel
    0.37
     RSC
    0.37
     থানায়
    0.36
     Scheduling
    0.36
    спе
    0.36
    ipe
    0.36
    Activations Density 0.001%

    No Known Activations