© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 12533
    Prev
    Next
    INDEX
    Explanations

    mattress, BetterHelp

    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_13_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
    id
    0.37
     april
    0.33
     rotary
    0.32
    s
    0.32
     fishing
    0.31
     {
    0.30
     Opa
    0.30
    spiration
    0.30
     April
    0.30
     spirit
    0.30
    POSITIVE LOGITS
     rhinophores
    0.34
    ܥ
    0.33
    їн
    0.31
    𝘸
    0.30
    𝕨
    0.30
    д
    0.29
    Ｗ
    0.29
    лк
    0.29
    𝐰
    0.29
    гі
    0.29
    Activations Density 0.010%

    No Known Activations