© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 257585
    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
     hunk
    1.25
    𝑺
    1.24
     vét
    1.23
     Palt
    1.22
    ऊदी
    1.21
     cleanser
    1.20
     Declaration
    1.17
     conciencia
    1.17
     entendu
    1.16
     terlebih
    1.16
    POSITIVE LOGITS
    ∘
    1.00
    verso
    0.91
     চলা
    0.90
     চলার
    0.90
    Με
    0.89
    ˶
    0.89
    ሞ
    0.88
    িয়া
    0.87
    fragt
    0.85
    ιο
    0.85
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.