© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 115967
    Prev
    Next
    INDEX
    Explanations

    And the worst part?

    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_27_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
     overflows
    0.39
     attest
    0.37
     decisively
    0.37
    齐
    0.37
     wanting
    0.35
     noteworthy
    0.35
     scour
    0.34
     เส้น
    0.34
    隙
    0.34
     motorized
    0.33
    POSITIVE LOGITS
     РФ
    0.43
    并非
    0.40
    旁邊
    0.39
    痉
    0.39
     ана
    0.38
    旁边
    0.38
     STILL
    0.38
     አይ
    0.38
     Corre
    0.38
    还将
    0.37
    Activations Density 0.009%

    No Known Activations