© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14284
    Prev
    Next
    INDEX
    Explanations

    unwieldy

    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_13_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
    闥
    0.13
    呥
    0.12
     das
    0.12
    ILLE
    0.12
     BAI
    0.12
    一定的
    0.12
    题目
    0.12
     levou
    0.12
     fume
    0.11
     dass
    0.11
    POSITIVE LOGITS
    }$;
    0.15
    credi
    0.15
    ny
    0.15
    ор
    0.14
    aborasi
    0.14
     users
    0.14
     ;
    0.13
    wijl
    0.13
    части
    0.13
    サーバ
    0.13
    Activations Density 0.005%

    No Known Activations