© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8311
    Prev
    Next
    INDEX
    Explanations

    is the

    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
    Certainly
    0.62
    로
    0.59
    क
    0.54
     autant
    0.53
    च
    0.53
    కి
    0.53
    ב
    0.52
    در
    0.52
     cheerleader
    0.51
     beanie
    0.51
    POSITIVE LOGITS
    zil
    0.66
    ➢
    0.61
    ниях
    0.61
    nickel
    0.60
    er
    0.59
    сора
    0.58
    el
    0.58
    heit
    0.58
    ותו
    0.57
    cology
    0.56
    Activations Density 0.318%

    No Known Activations