© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 77942
    Prev
    Next
    INDEX
    Explanations

    urls following "from" or "["

    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_29_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
     magnitudes
    0.36
     understandably
    0.35
    因
    0.34
     latitudine
    0.34
    陥
    0.33
     undef
    0.33
    ität
    0.33
    อย่าง
    0.33
     fined
    0.33
     sistem
    0.32
    POSITIVE LOGITS
    ždy
    0.41
    ダス
    0.39
    ర్చు
    0.38
     dajj
    0.38
     архіви
    0.38
    akti
    0.37
     kohta
    0.36
    Curs
    0.36
    跇
    0.36
    Successful
    0.36
    Activations Density 0.002%

    No Known Activations