© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 182450
    Prev
    Next
    INDEX
    Explanations

    systematic and logical approaches

    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_29_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
     dato
    0.37
     zhī
    0.36
    设备的
    0.35
     mineral
    0.35
     completos
    0.35
    inelli
    0.34
    ાગ
    0.33
     용
    0.33
     ලැබ
    0.33
     μετά
    0.32
    POSITIVE LOGITS
    संगिक
    0.40
     madness
    0.39
    рядок
    0.39
    Toward
    0.39
    濯
    0.39
    Suburb
    0.38
    Falling
    0.38
    getNumberOf
    0.38
    Movement
    0.38
    ymes
    0.38
    Activations Density 0.018%

    No Known Activations