© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 178481
    Prev
    Next
    INDEX
    Explanations

    execute experiments or 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_24_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
     potenza
    0.33
    の後
    0.33
     أَ
    0.31
    输
    0.29
    ifier
    0.29
    itatea
    0.29
     designates
    0.29
     premature
    0.29
     karane
    0.29
    듈
    0.29
    POSITIVE LOGITS
     einsch
    0.29
     πολλ
    0.28
     신고
    0.27
     sin
    0.27
     खुले
    0.27
    ལ
    0.27
    AA
    0.27
     scouting
    0.27
     pf
    0.26
    ക്കാന്‍
    0.26
    Activations Density 0.001%

    No Known Activations