© 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-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 257810
    Prev
    Next
    INDEX
    Explanations

    p-value

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_22_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
     reasons
    0.22
    ज्ञा
    0.21
    녠
    0.19
     taches
    0.19
     numbers
    0.19
     pagination
    0.19
    𝙫
    0.19
     losses
    0.18
    LAYOUT
    0.18
    톄
    0.18
    POSITIVE LOGITS
     დიდი
    0.19
     barge
    0.19
     Außerdem
    0.19
     misión
    0.18
     退
    0.18
    ayani
    0.18
     ใหญ่
    0.18
    đenja
    0.18
    ismillah
    0.18
     предвари
    0.18
    Activations Density 0.000%

    No Known Activations