© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 18813
    Prev
    Next
    INDEX
    Explanations

    served with

    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_15_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
     brind
    0.58
    s
    0.54
     adegu
    0.52
    вать
    0.50
    清新
    0.48
     realized
    0.47
     fro
    0.47
    缺陷
    0.47
    EDU
    0.46
    ୯
    0.46
    POSITIVE LOGITS
    மன்
    0.63
    अमेरिकी
    0.52
     consonants
    0.51
     θε
    0.50
    兒子
    0.49
    urrection
    0.49
     उच्चतम
    0.49
    了他的
    0.49
    ainer
    0.49
    unov
    0.49
    Activations Density 0.002%

    No Known Activations