© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B-IT
    3. 25-GEMMASCOPE-2-TRANSCODER-262K
    4. 9639
    Prev
    Next
    INDEX
    Explanations

    Transparency

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_25_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
     eyelids
    0.78
     sillonné
    0.69
    uniary
    0.68
     телефону
    0.67
     insoluble
    0.66
    Oi
    0.66
    ?}",
    0.65
    ptive
    0.64
    ړ
    0.64
    呢
    0.63
    POSITIVE LOGITS
     Paradise
    0.74
     सुरू
    0.71
     Nickel
    0.70
     Modal
    0.68
    daniel
    0.68
    ahit
    0.68
    Paradise
    0.68
     डू
    0.66
    ゲスト
    0.66
     اس
    0.65
    Activations Density 0.000%

    No Known Activations