© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 81534
    Prev
    Next
    INDEX
    Explanations

    comfort zone

    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_0_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
    Z
    1.43
    c
    1.41
    il
    1.35
    ing
    1.23
    In
    1.22
    ir
    1.20
    ী
    1.19
    in
    1.17
    ة
    1.15
    )};
    1.13
    POSITIVE LOGITS
    는
    1.34
    나
    1.30
     are
    1.26
    ке
    1.21
    dır
    1.20
    ні
    1.18
    기
    1.16
    いた
    1.14
    furan
    1.12
    се
    1.11
    Activations Density 0.001%

    No Known Activations