© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 239499
    Prev
    Next
    INDEX
    Explanations

    band score

    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_25_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
    ություն
    0.42
    దని
    0.42
    TempBuffer
    0.42
     एक्सरे
    0.40
    另一方面
    0.40
     რა
    0.40
     datafile
    0.40
    ᓵ
    0.39
    umento
    0.39
    athermy
    0.38
    POSITIVE LOGITS
    )}=\
    0.36
    zgl
    0.35
     kế
    0.35
     ezingu
    0.35
     inneh
    0.34
     tekl
    0.33
    zl
    0.33
     polygon
    0.33
    !}
    0.33
    立て
    0.32
    Activations Density 0.000%

    No Known Activations