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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-TRANSCODER-262K
    4. 77825
    Prev
    Next
    INDEX
    Explanations

    SYS followed by model or type

    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_31_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
    ↵
    0.28
     �
    0.27
    เนื้อ
    0.27
    <0x0B>
    0.25
    ም።
    0.25
     usually
    0.25
     नाटक
    0.25
     місто
    0.24
     rss
    0.24
     можно
    0.24
    POSITIVE LOGITS
    ₁,
    0.30
    ères
    0.29
     institut
    0.28
    ూరు
    0.28
     portions
    0.27
    Coef
    0.27
     institute
    0.26
    asiswa
    0.26
     ඉතා
    0.26
    pmod
    0.26
    Activations Density 0.007%

    No Known Activations