© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 176168
    Prev
    Next
    INDEX
    Explanations

    based

    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_24_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
     birdie
    0.43
    رحمن
    0.42
    ಟ್
    0.41
    ಷ
    0.41
     blouses
    0.40
     मल्टीप्लाई
    0.40
     logotipo
    0.40
     vermel
    0.39
     Είναι
    0.39
    ião
    0.39
    POSITIVE LOGITS
    CAD
    0.39
    דים
    0.37
     Accelerated
    0.36
    くれた
    0.36
     Marketing
    0.35
    覂
    0.35
    Vine
    0.34
     Library
    0.34
    Historically
    0.34
    急速
    0.33
    Activations Density 0.007%

    No Known Activations