© 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. 7365
    Prev
    Next
    INDEX
    Explanations

    Laser applications

    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
    ت
    3.22
    ين
    3.20
     tangga
    2.97
    ℕ
    2.95
    いきます
    2.89
    та
    2.87
    ak
    2.84
    अब
    2.81
    い
    2.79
    ية
    2.78
    POSITIVE LOGITS
    েশ
    2.63
    duplicated
    2.63
    ScriptAssemblies
    2.52
    xpress
    2.51
    Dan
    2.50
     речь
    2.49
    🅻
    2.43
    dword
    2.40
     sortBy
    2.40
    DependentUpon
    2.35
    Activations Density 0.030%

    No Known Activations