© 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. 8757
    Prev
    Next
    INDEX
    Explanations

    CoreDRAW CoppeliaSim userdetails Extensions

    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
     cosines
    0.84
    queous
    0.80
    个小时
    0.80
     stim
    0.78
    )})
    0.78
    -\{
    0.77
     equivalently
    0.73
    aż
    0.69
     denom
    0.69
     auch
    0.69
    POSITIVE LOGITS
    orul
    0.75
    etag
    0.74
    ftÂ
    0.71
    ाई
    0.70
    or
    0.70
     Eller
    0.70
    ró
    0.69
     Mathf
    0.69
    สัญญา
    0.69
    𝒔
    0.68
    Activations Density 0.002%

    No Known Activations