© 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. 202065
    Prev
    Next
    INDEX
    Explanations

    command argument

    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
    ᴊ
    0.40
     obstruct
    0.37
     Hers
    0.36
    িতা
    0.36
    듑
    0.35
    electrons
    0.35
     Tom
    0.34
    ività
    0.34
    indo
    0.34
    Specific
    0.34
    POSITIVE LOGITS
    ।’
    0.43
    നെയും
    0.39
     सोन
    0.39
     ‘
    0.37
     tzv
    0.37
    avacak
    0.35
     איי
    0.35
     exem
    0.35
     testim
    0.34
    dogan
    0.34
    Activations Density 0.005%

    No Known Activations