© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 15384
    Prev
    Next
    INDEX
    Explanations

    data size or block size

    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_34_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
     Flame
    0.46
    Flame
    0.46
     SUPPL
    0.42
    流
    0.41
    火焰
    0.41
     Flames
    0.40
     mong
    0.39
     trội
    0.39
     flame
    0.38
     Lighting
    0.38
    POSITIVE LOGITS
     dental
    0.68
     dentists
    0.68
    Dental
    0.67
    歯
    0.65
    dental
    0.64
     Dental
    0.63
     dentistry
    0.63
     tooth
    0.63
     Tooth
    0.63
    Tooth
    0.62
    Activations Density 0.052%

    No Known Activations