© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 107957
    Prev
    Next
    INDEX
    Explanations

    account-related codes

    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_2_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
    。
    1.52
    ان
    1.43
    از
    1.34
    لو
    1.33
    다
    1.30
    א
    1.30
    ため
    1.29
     is
    1.25
    는
    1.22
    是
    1.20
    POSITIVE LOGITS
    t
    1.21
    AY
    1.09
     εται
    1.08
     espagn
    1.05
     abusive
    1.04
    𝘁
    1.04
    𝑡
    1.03
     enfim
    1.02
     ακ
    1.02
     entrare
    1.02
    Activations Density 0.005%

    No Known Activations