© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 5376
    Prev
    Next
    INDEX
    Explanations

    fried rice instruction

    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_39_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
     Salaam
    0.43
     allah
    0.42
    ද
    0.42
    atie
    0.41
    𝔻
    0.41
    こ
    0.41
     BURE
    0.40
    łach
    0.40
    foregroundView
    0.38
     Hud
    0.38
    POSITIVE LOGITS
     abit
    0.43
     workable
    0.35
     uc
    0.35
    )$,
    0.34
    வதாக
    0.33
     potentials
    0.33
     sg
    0.33
    㛣
    0.33
     landed
    0.33
    LookAndFeel
    0.32
    Activations Density 0.044%

    No Known Activations