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

    Neuronpedia

    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. 30234
    Prev
    Next
    INDEX
    Explanations

    cors and Origin imports

    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
     csrf
    0.45
    ৮
    0.42
     boiler
    0.41
     CSR
    0.39
     Boiler
    0.38
    accesso
    0.38
     எட்டு
    0.38
     mengakses
    0.38
     INSERT
    0.37
    僟
    0.36
    POSITIVE LOGITS
    archiw
    0.37
    andal
    0.37
    idelity
    0.34
     Tes
    0.33
    tes
    0.33
    ালো
    0.33
     //#
    0.33
     pizarra
    0.33
     অবি
    0.32
     whipping
    0.32
    Activations Density 0.001%

    No Known Activations