© 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. 7462
    Prev
    Next
    INDEX
    Explanations

    android imports: util, widget, graphics, os

    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
    માં
    1.66
    هم
    1.58
    Во
    1.50
    ся
    1.47
    ని
    1.47
    ている
    1.43
    ی
    1.41
     interpolate
    1.41
     estudi
    1.40
    ت
    1.40
    POSITIVE LOGITS
    \!\
    1.42
    setShow
    1.39
     supposed
    1.28
     feasibility
    1.23
    ance
    1.22
     clapping
    1.20
     inherently
    1.20
    мо
    1.19
     atro
    1.19
    $`
    1.19
    Activations Density 0.000%

    No Known Activations