© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 130973
    Prev
    Next
    INDEX
    Explanations

    in advance

    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
    ة
    1.34
    ?
    0.95
    ాన్ని
    0.89
    في
    0.88
     أب
    0.87
    వ
    0.85
    ని
    0.83
     和
    0.83
    ني
    0.82
    在
    0.82
    POSITIVE LOGITS
    and
    1.04
    ri
    1.00
    re
    0.93
    c
    0.93
    one
    0.88
    than
    0.88
    toned
    0.88
    ut
    0.86
    time
    0.85
    about
    0.85
    Activations Density 0.002%

    No Known Activations