© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 100322
    Prev
    Next
    INDEX
    Explanations

    Twelfth Doctor, Eleventh Doctor

    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_14_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
    𒊭
    0.57
     aast
    0.56
    িয়
    0.55
     workstations
    0.55
     vineyards
    0.54
     ಕಟ್ಟ
    0.54
    㖷
    0.54
     editions
    0.53
     веке
    0.53
    硣
    0.53
    POSITIVE LOGITS
    não
    0.51
     neuro
    0.50
     humor
    0.50
    뻣
    0.50
    se
    0.49
     Mot
    0.49
     Bru
    0.49
    omotor
    0.49
    </i>
    0.49
     Crazy
    0.49
    Activations Density 0.000%

    No Known Activations