© 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. 8552
    Prev
    Next
    INDEX
    Explanations

    like all

    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
    ع
    1.35
    ン
    1.08
    at
    1.04
     thirds
    1.01
    ל
    0.98
     siitä
    0.98
     fielder
    0.98
     eens
    0.98
     angeles
    0.96
     samh
    0.96
    POSITIVE LOGITS
    いますが
    1.23
     insan
    1.00
    молча
    0.95
     metų
    0.93
    ˩
    0.92
    ᠠ
    0.90
    ো
    0.89
     رہتا
    0.88
    륵
    0.87
    ğı
    0.86
    Activations Density 0.158%

    No Known Activations