© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 261016
    Prev
    Next
    INDEX
    Explanations

    ecology or

    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_5_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
     as
    1.70
    ’
    1.33
    (
    1.09
    ang
    1.06
    ει
    1.03
    k
    1.01
    za
    0.96
    )};
    0.96
    .\\
    0.91
    .`
    0.91
    POSITIVE LOGITS
    ة
    1.41
    in
    1.36
    ও
    1.32
    어
    1.31
    ли
    1.27
    ম
    1.21
    я
    1.20
    い
    1.17
     MTN
    1.12
    한
    1.11
    Activations Density 0.000%

    No Known Activations