© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 211240
    Prev
    Next
    INDEX
    Explanations

    business and organizations

    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_5_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
    س
    0.53
    ס
    0.51
    ти
    0.49
    )
    0.47
    an
    0.44
    }
    0.42
    ১৯
    0.42
    ش
    0.41
    も
    0.40
    ;
    0.39
    POSITIVE LOGITS
    ká
    0.49
     by
    0.46
    ка
    0.46
     of
    0.45
    ाने
    0.42
     that
    0.42
    3
    0.40
    м
    0.40
    ви
    0.40
    دة
    0.38
    Activations Density 0.008%

    No Known Activations