© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    4. 77835
    Prev
    Next
    INDEX
    Explanations

    else:

    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_31_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
    rière
    0.28
     pisos
    0.24
    ាំ
    0.23
    격을
    0.22
    ì
    0.22
     Cause
    0.21
    rogram
    0.21
     étage
    0.21
     Continuous
    0.21
    inn
    0.20
    POSITIVE LOGITS
     кир
    0.25
     Abou
    0.25
     ছাড়াই
    0.25
     dispense
    0.24
    Abasis
    0.24
    渲
    0.24
     Gabriele
    0.24
     ينت
    0.24
    apon
    0.24
    cedores
    0.24
    Activations Density 0.002%

    No Known Activations