© 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. 8160
    Prev
    Next
    INDEX
    Explanations

    google .com domains and Australian Rules Football

    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
     paraphrase
    3.13
    ار
    2.53
    arote
    2.49
    я
    2.41
    ように
    2.33
     forefront
    2.31
     simplest
    2.28
    sız
    2.27
    ിയ
    2.25
    idée
    2.24
    POSITIVE LOGITS
    an
    3.20
    ان
    2.77
    '_
    2.58
     longtemps
    2.39
     bosons
    2.39
     telle
    2.38
    row
    2.26
    ोत्तर
    2.25
     skulls
    2.24
    TERS
    2.24
    Activations Density 0.000%

    No Known Activations