© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 209554
    Prev
    Next
    INDEX
    Explanations

    identity matrix I

    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_20_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
    simmons
    0.36
    কানিক্যাল
    0.35
     transmission
    0.35
     socioeconomic
    0.35
     community
    0.34
    ongs
    0.34
     scrimmage
    0.34
    ಟ
    0.34
     pelvic
    0.33
    kungan
    0.33
    POSITIVE LOGITS
     A
    0.44
     Förder
    0.42
     Are
    0.40
     Frau
    0.39
     Kön
    0.37
    Are
    0.37
     ähn
    0.37
     Christophe
    0.36
     Astrid
    0.35
     Hosts
    0.35
    Activations Density 0.001%

    No Known Activations