© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 9087
    Prev
    Next
    INDEX
    Explanations

    HTML style tags

    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_40_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
    reciate
    0.35
    ortal
    0.34
     cooker
    0.32
     REPUBLIC
    0.32
    အား
    0.32
    ゞ
    0.32
    ದಲ್ಲ
    0.32
    ቻ
    0.31
     zlat
    0.30
    ﭼ
    0.30
    POSITIVE LOGITS
    soon
    0.34
    finement
    0.34
     Raise
    0.34
    jun
    0.33
     khóa
    0.33
    BlockUsed
    0.33
    よう
    0.32
     静
    0.32
    King
    0.32
    种子
    0.32
    Activations Density 0.005%

    No Known Activations