© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6781
    Prev
    Next
    INDEX
    Explanations

    URLs and citations

    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_39_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
    꽁
    0.42
     नाबाद
    0.41
    PropertySheets
    0.39
    ᷅
    0.37
     विघ
    0.37
    𒊑
    0.37
    гистра
    0.36
     sulfates
    0.36
    ordelen
    0.36
    砒
    0.36
    POSITIVE LOGITS
     X
    0.42
    ulint
    0.41
    bd
    0.41
    /
    0.40
     therapy
    0.38
    pur
    0.38
    BI
    0.37
     BI
    0.37
     Blau
    0.36
    óg
    0.36
    Activations Density 0.001%

    No Known Activations