© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 199570
    Prev
    Next
    INDEX
    Explanations

    train data files

    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_27_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
    녕하십니까
    0.37
    }^
    0.36
     tine
    0.36
     adver
    0.36
     comulti
    0.35
     manus
    0.35
    cra
    0.35
    crs
    0.34
    JOSE
    0.34
     feder
    0.34
    POSITIVE LOGITS
     মারাত্মক
    0.44
     Methodology
    0.40
    btnLogout
    0.38
    ريح
    0.37
     ভয়ানক
    0.37
     核
    0.36
     выходит
    0.36
    Beauty
    0.36
    កំណត់
    0.36
    FieldError
    0.36
    Activations Density 0.001%

    No Known Activations