© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 98757
    Prev
    Next
    INDEX
    Explanations

    instruction word

    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_14_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
     powied
    0.46
    ค
    0.45
    Decoding
    0.45
     x
    0.43
    𝐭
    0.43
     Idi
    0.42
    ચી
    0.41
     chiff
    0.40
    Idi
    0.40
    𝐜
    0.39
    POSITIVE LOGITS
    الن
    0.46
    ле
    0.46
    rilor
    0.45
    raa
    0.43
     由于
    0.42
    ಗರ
    0.42
     যেহেতু
    0.41
     فن
    0.41
    উন
    0.41
     नगरपालिका
    0.41
    Activations Density 0.003%

    No Known Activations