© 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. 8623
    Prev
    Next
    INDEX
    Explanations

    watered 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
    SACTION
    2.64
    đe
    2.50
    imantan
    2.49
    𝓉
    2.48
    य
    2.38
     tidy
    2.33
     prosecution
    2.30
     pioneering
    2.30
     mammoth
    2.28
     disables
    2.27
    POSITIVE LOGITS
    ten
    2.96
    ো
    2.75
    िंग
    2.70
    il
    2.67
     suche
    2.48
    র
    2.47
    ro
    2.45
    ﮢ
    2.39
    あれば
    2.36
    ă
    2.34
    Activations Density 0.000%

    No Known Activations