© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 171945
    Prev
    Next
    INDEX
    Explanations

    section or part

    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_20_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
     तसेच
    0.18
    ảy
    0.17
    }},
    0.16
    ruzione
    0.16
     पूर्
    0.16
     „
    0.16
    लेषण
    0.16
    ę
    0.15
     ,,
    0.15
    ifik
    0.15
    POSITIVE LOGITS
     hike
    0.16
    校
    0.16
     ओटी
    0.16
    Boe
    0.16
    shoring
    0.15
    IIT
    0.15
    IVERY
    0.15
     salle
    0.15
     হেতু
    0.15
    迭代
    0.15
    Activations Density 0.001%

    No Known Activations