© 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. 7871
    Prev
    Next
    INDEX
    Explanations

    hugging face links

    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
    ानों
    1.05
     kites
    1.03
     Forgot
    1.03
     Kembali
    1.03
    dateTime
    1.01
    🅽
    1.01
     dział
    1.01
    े
    1.00
     saiu
    0.99
     Jerman
    0.98
    POSITIVE LOGITS
    н
    1.02
    "*
    1.01
    oltre
    1.01
    т
    0.93
    zené
    0.91
    "$
    0.90
    "')
    0.90
    ⁧
    0.89
    arccos
    0.88
    сибо
    0.87
    Activations Density 0.005%

    No Known Activations