© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 25390
    Prev
    Next
    INDEX
    Explanations

    THIS STANDS FOR

    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_10_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
    ॉय
    0.60
    ной
    0.56
    ，
    0.55
     игровой
    0.53
     we
    0.52
    ва
    0.51
    ،
    0.51
    ानी
    0.47
    मय
    0.47
    ный
    0.47
    POSITIVE LOGITS
     langen
    0.60
     Pei
    0.57
     kuba
    0.56
     Insgesamt
    0.55
    }\
    0.55
     dieser
    0.55
    אם
    0.55
    }}\
    0.54
    }}-\
    0.54
     größeren
    0.54
    Activations Density 0.022%

    No Known Activations