© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 2625
    Prev
    Next
    INDEX
    Explanations

    LM Studio and cart

    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_39_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
     zoom
    0.35
    cadilly
    0.35
    rsfs
    0.35
     Autos
    0.34
    棌
    0.33
    र्गत
    0.32
     تړ
    0.32
    廟
    0.31
    肇
    0.31
     penetrating
    0.31
    POSITIVE LOGITS
     Dashboard
    0.37
    CodeGen
    0.35
    Ronald
    0.34
     Lel
    0.34
    Dashboard
    0.33
    Protected
    0.33
    profile
    0.32
    Global
    0.32
     dashboard
    0.32
    dashboard
    0.32
    Activations Density 0.018%

    No Known Activations