© 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
    2. Gemma-3-27B-IT
    3. 13-GEMMASCOPE-2-TRANSCODER-262K
    4. 165264
    Prev
    Next
    INDEX
    Explanations

    stage, face, California, platform

    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
     limelight
    0.56
    迩
    0.52
     filth
    0.52
     Keine
    0.51
     almighty
    0.50
     executar
    0.49
    Читати
    0.49
     backyard
    0.49
    륨
    0.49
    ரீ
    0.48
    POSITIVE LOGITS
     a
    0.54
    а
    0.47
    \
    0.45
     What
    0.44
    </
    0.43
    о
    0.43
     S
    0.43
    AN
    0.43
     A
    0.42
    atal
    0.42
    Activations Density 0.000%

    No Known Activations