© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 196501
    Prev
    Next
    INDEX
    Explanations

    ust

    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_9_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
    ’
    0.41
    തി
    0.32
    غ
    0.31
     appetizers
    0.30
    𝙶
    0.30
     malignancies
    0.29
    あげ
    0.28
     visualizations
    0.28
    ት
    0.28
    િંગ
    0.28
    POSITIVE LOGITS
    at
    0.44
    EE
    0.36
    an
    0.35
     l
    0.33
     will
    0.32
    as
    0.31
    i
    0.31
    一股
    0.31
    는
    0.31
     וא
    0.30
    Activations Density 0.000%

    No Known Activations