© 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. 7944
    Prev
    Next
    INDEX
    Explanations

    torch.nn

    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
    ங்கிணை
    0.68
    nbsp
    0.65
    چه
    0.63
    ks
    0.61
    ني
    0.57
    ksi
    0.57
    𝘪
    0.56
    gs
    0.56
    ιση
    0.56
    ki
    0.56
    POSITIVE LOGITS
     preponderance
    0.66
     omit
    0.64
    deviceId
    0.63
     unify
    0.63
     prepend
    0.62
     ulo
    0.61
    い
    0.60
     arsen
    0.59
     dorp
    0.58
     facades
    0.58
    Activations Density 0.020%

    No Known Activations