© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 453
    Prev
    Next
    INDEX
    Explanations

    axis tracking

    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
    ธาน
    0.45
    മിക
    0.43
    wana
    0.39
    GLuint
    0.39
    ifiques
    0.38
    ರ್ಗ
    0.37
     Grup
    0.37
    ၄
    0.37
    athon
    0.36
     жизни
    0.35
    POSITIVE LOGITS
     loop
    0.51
     looped
    0.48
     Loop
    0.47
     loops
    0.47
    Loop
    0.45
    ループ
    0.44
    loop
    0.44
     Loops
    0.40
    looped
    0.40
    itemList
    0.40
    Activations Density 0.000%

    No Known Activations