© 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. 29896
    Prev
    Next
    INDEX
    Explanations

    Munich

    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
    çi
    0.46
    Austria
    0.39
    Swiss
    0.39
     Швейца
    0.39
     সুইস
    0.38
    swiss
    0.38
    /%
    0.37
    اک
    0.37
    Atoi
    0.36
     Austria
    0.36
    POSITIVE LOGITS
     Spor
    0.41
    <0x95>
    0.41
     Exit
    0.40
     Quarantine
    0.40
     Michigan
    0.39
     Inside
    0.39
     exit
    0.38
     Dispatch
    0.38
     Houses
    0.38
     Toyota
    0.38
    Activations Density 0.014%

    No Known Activations