© 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. 6976
    Prev
    Next
    INDEX
    Explanations

    a couple of

    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
    eau
    2.06
     јед
    1.99
    螂
    1.96
    astrophe
    1.93
    ope
    1.92
    おそらく
    1.88
     olympiques
    1.85
    ための
    1.84
    ljivo
    1.84
    سازی
    1.83
    POSITIVE LOGITS
     dozen
    3.55
    dozen
    3.13
     hundred
    2.82
     thousand
    2.77
    thousand
    2.38
    Pagination
    2.37
    tale
    2.35
    ू
    2.35
    Hundred
    2.30
    年前
    2.24
    Activations Density 0.034%

    No Known Activations