© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 9247
    Prev
    Next
    INDEX
    Explanations

    abbreviations

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_25_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
    hetically
    0.83
    放
    0.79
    Desktop
    0.77
    வினை
    0.72
    ذب
    0.71
    Optical
    0.70
    attached
    0.69
     oxidase
    0.69
    Inde
    0.67
    ⓔ
    0.66
    POSITIVE LOGITS
    उ
    0.62
     guidance
    0.62
    உ
    0.61
     Constants
    0.61
     united
    0.60
    <unused64>
    0.59
     Unter
    0.59
     మద్యం
    0.59
    မ
    0.59
     nine
    0.59
    Activations Density 0.015%

    No Known Activations