© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 60028
    Prev
    Next
    INDEX
    Explanations

    journaling practices

    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_11_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
    9
    0.68
    6
    0.65
     palindrome
    0.59
     majeure
    0.58
    5
    0.54
    LY
    0.54
     né
    0.53
     mythology
    0.53
     Cultural
    0.52
    Cultural
    0.52
    POSITIVE LOGITS
    깥
    0.63
    тувати
    0.63
     afuera
    0.62
    とした
    0.61
     Anfield
    0.61
     Schwer
    0.61
    सेट
    0.61
    োড
    0.60
     effetto
    0.60
     सूरत
    0.59
    Activations Density 0.074%

    No Known Activations