© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 241227
    Prev
    Next
    INDEX
    Explanations

    originating place descriptions

    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_25_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
    MDg
    0.38
     स्टेशनों
    0.37
     obrigado
    0.36
    ={"
    0.36
    yson
    0.35
     বাহুল্য
    0.35
     теркә
    0.34
     copertura
    0.34
     pergunt
    0.33
    および
    0.33
    POSITIVE LOGITS
     comparative
    0.42
     അറിയ
    0.42
     proven
    0.39
     Ча
    0.38
     事
    0.38
     stormy
    0.37
    บท
    0.37
     Gaelic
    0.36
     any
    0.36
    Comparative
    0.36
    Activations Density 0.002%

    No Known Activations