© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 172200
    Prev
    Next
    INDEX
    Explanations

    numbers 0.0 to 1.0

    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_20_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
    em
    0.47
    Con
    0.43
    C
    0.43
     Con
    0.43
    W
    0.43
    IP
    0.42
    CON
    0.41
    ⁶
    0.41
    _
    0.41
    comb
    0.40
    POSITIVE LOGITS
     recoger
    0.50
     бясплат
    0.45
     gioc
    0.45
     zape
    0.45
     लियो
    0.44
    𝟑
    0.44
    箏
    0.43
     Pyramid
    0.43
    ጋገብ
    0.43
    ᱒
    0.43
    Activations Density 0.001%

    No Known Activations