© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 258911
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_10_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
    eded
    1.08
    letal
    1.02
    ূনতম
    1.00
     richied
    1.00
     Houghton
    1.00
    აქ
    0.95
    }".
    0.95
    <bos>
    0.94
     iniziamo
    0.93
     habrá
    0.93
    POSITIVE LOGITS
    IS
    1.41
    arrays
    1.40
     Beaucoup
    1.38
     аж
    1.27
    ra
    1.27
     интел
    1.25
    पर
    1.21
    yay
    1.21
     বাঙালী
    1.20
     нем
    1.20
    Activations Density 0.000%

    No Known Activations