© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 209421
    Prev
    Next
    INDEX
    Explanations

    code keywords (if, const, try)

    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_20_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
    \}$,
    0.32
    पूर्ण
    0.32
     प्रि
    0.32
    $$\
    0.31
    ]$,
    0.30
     gimnaz
    0.30
    $[
    0.30
    }]$,
    0.30
     graduates
    0.30
     quadri
    0.30
    POSITIVE LOGITS
     sayings
    0.31
    说到
    0.31
    IgnoreCase
    0.29
    aseña
    0.29
     switches
    0.29
    ಿಸಿದ
    0.28
    位数
    0.28
     verwenden
    0.28
     విషయంలో
    0.27
    десь
    0.27
    Activations Density 0.002%

    No Known Activations