© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 261320
    Prev
    Next
    INDEX
    Explanations

    Velo, Princess, message, Id

    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_5_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
    ;
    1.53
    to
    1.33
    as
    1.26
    ו
    1.16
    {
    1.03
    <0x80>
    1.00
    o
    0.99
    ০০
    0.94
    }
    0.92
    an
    0.91
    POSITIVE LOGITS
    ل
    1.39
    ের
    1.23
    いた
    1.21
    ی
    1.12
     Đầu
    1.10
    ים
    1.07
    Ин
    1.04
    ವ್
    1.04
     Акы
    1.02
    ों
    1.02
    Activations Density 0.000%

    No Known Activations