© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 31485
    Prev
    Next
    INDEX
    Explanations

    e followed by 8 or esm

    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
     decidió
    0.40
     whanne
    0.38
     mint
    0.38
     Marino
    0.38
     refinement
    0.37
     Loyal
    0.37
     loadAnimation
    0.37
    澧
    0.36
     passt
    0.36
     hjust
    0.36
    POSITIVE LOGITS
    These
    0.39
    これらの
    0.38
    ug
    0.38
    suited
    0.37
     These
    0.36
    łuż
    0.36
    қан
    0.36
    transport
    0.35
     эти
    0.35
    от
    0.35
    Activations Density 0.017%

    No Known Activations