© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 91116
    Prev
    Next
    INDEX
    Explanations

    programming and language

    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_60_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
     P
    0.46
     פּ
    0.45
     ପ
    0.44
     ਪ
    0.42
     PP
    0.41
    ིན་
    0.37
    娆
    0.36
     ព
    0.36
    RawO
    0.36
     პ
    0.35
    POSITIVE LOGITS
    po
    1.41
    par
    1.41
    pu
    1.41
    pen
    1.39
    پ
    1.39
    по
    1.37
    por
    1.36
    pa
    1.36
    pat
    1.35
    pan
    1.35
    Activations Density 0.177%

    No Known Activations