© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 130663
    Prev
    Next
    INDEX
    Explanations

    people often

    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_6_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
    на
    0.96
    к
    0.94
    л
    0.93
    б
    0.83
    ба
    0.80
    ल
    0.79
    ก
    0.79
    чі
    0.76
    ι
    0.76
    为
    0.75
    POSITIVE LOGITS
    ra
    0.98
    w
    0.96
    a
    0.91
    m
    0.91
    writing
    0.90
    noxious
    0.89
    tive
    0.89
    고
    0.88
    ar
    0.86
    ه
    0.86
    Activations Density 0.019%

    No Known Activations