© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 2461
    Prev
    Next
    INDEX
    Explanations

    media format types

    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_38_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
    पूर्ति
    0.38
    انيا
    0.37
    𝘃
    0.37
     prévenir
    0.37
     isos
    0.36
     мае
    0.35
     रमा
    0.35
     Gaston
    0.34
    umbra
    0.34
    俢
    0.34
    POSITIVE LOGITS
     format
    0.89
     Format
    0.84
    Format
    0.83
     formats
    0.83
    format
    0.81
    FORMAT
    0.78
     formato
    0.75
    格式
    0.74
     FORMAT
    0.71
    Formats
    0.71
    Activations Density 0.026%

    No Known Activations