© 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. 167470
    Prev
    Next
    INDEX
    Explanations

    PLUGIN, CLASS, BUFFER, RESOURCE

    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
    }`,
    0.32
    iera
    0.32
     Baat
    0.31
     resort
    0.30
    लता
    0.30
     guess
    0.30
     indirect
    0.29
     cocoon
    0.29
    Lora
    0.29
     obsession
    0.29
    POSITIVE LOGITS
     दर्जा
    0.33
    原因是
    0.32
    assertEqual
    0.32
    Ҡ
    0.32
    Durham
    0.31
    áp
    0.31
    Maps
    0.31
    )]);
    0.31
    Ҭ
    0.31
     .(
    0.30
    Activations Density 0.001%

    No Known Activations