© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 34127
    Prev
    Next
    INDEX
    Explanations

    indigenous groups, communities

    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_7_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
    o
    0.18
     at
    0.17
    a
    0.17
     with
    0.14
    c
    0.14
    g
    0.13
     one
    0.13
     Pathways
    0.12
    e
    0.12
     l
    0.12
    POSITIVE LOGITS
    ת
    0.21
    т
    0.18
    Β
    0.17
    Ж
    0.16
    Đ
    0.16
    Το
    0.16
    ත
    0.15
    Η
    0.15
    Во
    0.15
    تبر
    0.15
    Activations Density 0.000%

    No Known Activations