© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 7202
    Prev
    Next
    INDEX
    Explanations

    code snippets, library prefixes, xml tags

    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
    霾
    0.38
    రే
    0.38
    amore
    0.37
     GAMMA
    0.36
    visitors
    0.35
    തല
    0.35
     হারা
    0.35
     Oll
    0.35
     Gé
    0.35
    FIGURE
    0.35
    POSITIVE LOGITS
     blinds
    0.38
     ext
    0.37
    秽
    0.36
    挡
    0.36
    azion
    0.36
    ޅ
    0.35
     Miy
    0.35
    dateFormat
    0.35
    ര്യ
    0.35
     Yuan
    0.34
    Activations Density 0.035%

    No Known Activations