© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 6365
    Prev
    Next
    INDEX
    Explanations

    transactional actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_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
    та
    3.73
     inscrib
    3.19
    𝒗
    2.90
    гот
    2.79
    t
    2.74
    साइटी
    2.72
     thousand
    2.71
    cstdio
    2.70
    𝒆
    2.63
    س
    2.60
    POSITIVE LOGITS
    er
    3.96
    erade
    2.92
    ു
    2.79
    龴
    2.78
    ر
    2.72
    posable
    2.71
     сообщает
    2.63
     prisms
    2.59
    Subsequently
    2.57
    ⠀⠀⠀⠀
    2.53
    Activations Density 0.037%

    No Known Activations