© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-TRANSCODER-262K
    4. 10675
    Prev
    Next
    INDEX
    Explanations

    read aloud or mentor actions

    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_40_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
    echen
    0.38
    ligence
    0.38
    UTO
    0.36
    bours
    0.36
    pedo
    0.36
    ryn
    0.35
     Pram
    0.35
     伊
    0.35
    fila
    0.34
    xym
    0.34
    POSITIVE LOGITS
     read
    0.71
    read
    0.59
     aloud
    0.51
    Read
    0.49
     Read
    0.49
     क्रांति
    0.45
     mentor
    0.41
    Mentor
    0.40
     READ
    0.40
     Mentor
    0.40
    Activations Density 0.098%

    No Known Activations