© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 31471
    Prev
    Next
    INDEX
    Explanations

    script related actions

    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_40_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
     choices
    0.45
     Sloane
    0.44
    choices
    0.42
    ත්‍
    0.42
    Choices
    0.42
    شن
    0.39
    眝
    0.38
     Choices
    0.38
    ˑ
    0.38
    playable
    0.37
    POSITIVE LOGITS
     script
    1.08
     tele
    1.00
     scripts
    0.93
    script
    0.92
    Tele
    0.91
     Tele
    0.89
    tele
    0.84
     Script
    0.84
     Scripts
    0.76
     स्क्रिप्ट
    0.76
    Activations Density 0.071%

    No Known Activations