© 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. 7295
    Prev
    Next
    INDEX
    Explanations

    eyewitness, eyeglass, eyes, ocular, reflex, opening

    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
    তম
    2.47
    부터
    2.40
    ف
    2.33
    िक
    2.33
    б
    2.28
    xor
    2.25
     dicho
    2.22
    ुणा
    2.22
     leído
    2.20
    ων
    2.19
    POSITIVE LOGITS
    л
    2.88
     attention
    2.71
     👀
    2.63
     asynchronous
    2.50
    lash
    2.50
    opener
    2.46
    ком
    2.46
     elapsed
    2.46
     transpiration
    2.42
    ков
    2.37
    Activations Density 0.048%

    No Known Activations