© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 205055
    Prev
    Next
    INDEX
    Explanations

    top [institution type]

    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_37_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
    ាច់
    0.42
    伌
    0.40
    `);
    0.38
     radionuclides
    0.38
    }');
    0.38
    φέρον
    0.37
    xcodeproj
    0.37
    毎日
    0.37
     />;
    0.36
     ubicación
    0.36
    POSITIVE LOGITS
     few
    0.45
    azas
    0.40
     wenige
    0.39
     wenigen
    0.39
    few
    0.38
     немно
    0.37
     quelques
    0.37
     meters
    0.36
     unpre
    0.36
     minimalist
    0.36
    Activations Density 0.001%

    No Known Activations