© 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. 7195
    Prev
    Next
    INDEX
    Explanations

    dive into, break down

    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
    ेल
    0.78
     zealand
    0.68
    े
    0.65
    ت
    0.63
    т
    0.61
     uffic
    0.61
     чином
    0.61
    ет
    0.60
    ➹
    0.58
    astype
    0.58
    POSITIVE LOGITS
    of
    0.52
    ان
    0.50
    ución
    0.49
     непри
    0.49
    an
    0.49
     anum
    0.48
    Elsewhere
    0.46
    oš
    0.44
    one
    0.44
    klore
    0.44
    Activations Density 1.827%

    No Known Activations