© 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. 7664
    Prev
    Next
    INDEX
    Explanations

    goes on to

    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
    𝙙
    1.05
    ../../
    0.98
     výro
    0.98
     phyto
    0.97
    เจน
    0.97
    鳌
    0.91
     leisurely
    0.90
     tudi
    0.90
    ்துற
    0.89
    ں
    0.87
    POSITIVE LOGITS
    ة
    1.40
    ed
    1.19
    ת
    0.94
    紝
    0.92
    ع
    0.90
    য়
    0.88
    ن
    0.87
    er
    0.86
    علم
    0.86
    ва
    0.86
    Activations Density 0.006%

    No Known Activations