© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 89527
    Prev
    Next
    INDEX
    Explanations

    blueprint and plans

    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_18_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
    Responsible
    0.46
    焱
    0.46
    Environmental
    0.45
    mitters
    0.43
    గి
    0.42
    Dry
    0.42
     тем
    0.42
    匼
    0.42
    щи
    0.42
     تیاری
    0.41
    POSITIVE LOGITS
    oue
    0.51
     Claire
    0.50
     ghostly
    0.48
     allow
    0.48
     Ã
    0.47
     admirably
    0.47
     klubu
    0.46
     merr
    0.45
     ホ
    0.45
     affirms
    0.45
    Activations Density 0.002%

    No Known Activations