© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 261228
    Prev
    Next
    INDEX
    Explanations

    bem, mal, bien

    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_5_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
    -
    1.41
    ;
    1.38
     in
    1.27
     σε
    1.02
     яким
    0.99
    त
    0.98
     alem
    0.95
     (
    0.95
    त्ति
    0.94
     mutta
    0.93
    POSITIVE LOGITS
    s
    1.50
    1
    1.40
    ের
    1.38
    8
    1.37
    There
    1.36
    3
    1.35
    It
    1.33
    ش
    1.31
    7
    1.30
    ORS
    1.27
    Activations Density 0.001%

    No Known Activations