© 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. 89188
    Prev
    Next
    INDEX
    Explanations

    menil.org, MNLI, Manila Bay, Menelik II

    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
    mé
    0.78
    s
    0.73
    C
    0.71
    nici
    0.70
    gång
    0.70
    mqtt
    0.68
    F
    0.68
    ovat
    0.67
    К
    0.67
    W
    0.66
    POSITIVE LOGITS
    -
    0.80
    ור
    0.78
    ้
    0.74
    ET
    0.71
    י
    0.70
     entice
    0.70
    ATION
    0.69
    т
    0.68
    ,",
    0.67
    ই
    0.67
    Activations Density 0.000%

    No Known Activations