© 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. 8362
    Prev
    Next
    INDEX
    Explanations

    Scores like 1-0 or 3-0

    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
    輯
    1.10
    става
    1.02
    жды
    1.00
    orption
    0.98
     cherish
    0.97
    лъ
    0.96
    緞
    0.96
     freshly
    0.95
    icción
    0.93
     ули
    0.93
    POSITIVE LOGITS
    𝘻
    1.17
    𝘨
    1.05
    ن
    1.04
    𝘳
    1.00
    제목
    0.98
    linspace
    0.96
    goers
    0.95
    r
    0.95
    ے
    0.94
    द्योगिकी
    0.94
    Activations Density 0.006%

    No Known Activations