© 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. 8491
    Prev
    Next
    INDEX
    Explanations

    frequently asked questions

    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
    ar
    3.29
    म
    2.49
    𝘺
    2.47
    سي
    2.42
     ஆண்டு
    2.40
    يام
    2.30
    ことが
    2.29
    arag
    2.25
    ع
    2.25
    тря
    2.20
    POSITIVE LOGITS
     اوقات
    3.50
     Asked
    3.04
     times
    2.97
    kali
    2.82
     intellig
    2.82
     overlooked
    2.78
    times
    2.76
     бывает
    2.64
     defaultdict
    2.64
     Características
    2.56
    Activations Density 0.184%

    No Known Activations