© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 20448
    Prev
    Next
    INDEX
    Explanations

    writing

    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_56_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
    дят
    0.43
     leído
    0.38
    ichen
    0.37
    \:
    0.34
    搂
    0.33
    }~\
    0.32
    niew
    0.32
    习
    0.32
     товар
    0.32
     পাত
    0.32
    POSITIVE LOGITS
     writing
    2.72
     Writing
    2.44
    writing
    2.27
    Writing
    2.25
    写作
    1.49
     लेखन
    1.36
    écriture
    1.25
     scrittura
    1.23
     escritura
    1.16
     লেখার
    1.09
    Activations Density 0.253%

    No Known Activations