© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 87669
    Prev
    Next
    INDEX
    Explanations

    azure web jobs, boards, drake, ad, app

    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_3_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
    al
    0.74
    ل
    0.67
    te
    0.62
    i
    0.61
    anath
    0.59
    ल
    0.59
     }}$.
    0.59
    ัน
    0.58
    atation
    0.57
    ig
    0.57
    POSITIVE LOGITS
    CS
    0.70
    CM
    0.66
    5
    0.64
    TS
    0.64
    4
    0.63
    },
    0.63
    Sp
    0.61
    );
    0.61
    ),
    0.61
     for
    0.60
    Activations Density 0.003%

    No Known Activations