© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 241852
    Prev
    Next
    INDEX
    Explanations

    microscopic damage

    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
     المف
    0.46
    ikat
    0.38
     ගැනීම
    0.36
    タリア
    0.36
     brightly
    0.35
     Coins
    0.35
    ICATION
    0.35
    怀
    0.34
    roduction
    0.34
     sbParams
    0.34
    POSITIVE LOGITS
     micro
    1.54
     Micro
    1.43
    微
    1.42
     микро
    1.38
    micro
    1.37
    Micro
    1.37
     mikro
    1.26
     microscopic
    1.21
     microm
    1.16
     Mikro
    1.14
    Activations Density 0.081%

    No Known Activations