© 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. 207631
    Prev
    Next
    INDEX
    Explanations

    IPs, names, scores, or weights

    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
    देशक
    0.34
     फेव
    0.34
     pubescence
    0.33
    וֹ
    0.32
     antisymmetric
    0.32
    生产者
    0.32
    ীতে
    0.31
    𝓗
    0.31
     grammaticality
    0.31
     অপরিচিত
    0.31
    POSITIVE LOGITS
    s
    0.34
    9
    0.34
    rel
    0.31
    ウン
    0.29
     rel
    0.29
    op
    0.29
     _
    0.28
     Get
    0.28
     do
    0.28
    3
    0.28
    Activations Density 0.005%

    No Known Activations