© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 82997
    Prev
    Next
    INDEX
    Explanations

    painless sores or swelling or continue

    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_0_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
    л
    1.84
     that
    1.74
    ل
    1.53
     که
    1.44
    나가
    1.40
     to
    1.39
    that
    1.38
     اکرم
    1.36
    मुळे
    1.34
    ことで
    1.31
    POSITIVE LOGITS
    ين
    1.80
    n
    1.70
    人
    1.43
    在
    1.38
    IN
    1.34
    ir
    1.27
    ’
    1.27
    ا
    1.23
    0
    1.16
    ent
    1.15
    Activations Density 0.000%

    No Known Activations