© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 120490
    Prev
    Next
    INDEX
    Explanations

    thread-safe

    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_27_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
     समोर
    0.18
    ret
    0.17
     neka
    0.16
     $
    0.16
    riendo
    0.16
     मिलकर
    0.16
    retrieve
    0.15
     ટી
    0.15
     manje
    0.15
     Convert
    0.15
    POSITIVE LOGITS
     गुर्जर
    0.21
    duced
    0.20
    𝒹
    0.19
    विटी
    0.18
     realtà
    0.18
    𒌉
    0.18
    KeyboardView
    0.18
    িকাংশ
    0.18
    现实
    0.18
    ム
    0.18
    Activations Density 0.000%

    No Known Activations