© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 13742
    Prev
    Next
    INDEX
    Explanations

    max_tokens and n=1

    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_40_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
    }$')
    0.40
     пока
    0.38
     tội
    0.38
     recur
    0.37
     annotations
    0.37
     修改
    0.37
    íonn
    0.37
     annotation
    0.37
    文本
    0.35
     നില
    0.35
    POSITIVE LOGITS
     Kru
    0.38
     сада
    0.38
    共
    0.38
     fewer
    0.37
     liczb
    0.37
    ipan
    0.37
     kru
    0.36
     পয়
    0.36
    ็ก
    0.35
    蟲
    0.35
    Activations Density 0.001%

    No Known Activations