© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 162405
    Prev
    Next
    INDEX
    Explanations

    Car and Driver / begins

    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_2_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
    ה
    1.27
    se
    1.26
    я
    1.25
    са
    1.23
    י
    1.23
    ي
    1.19
    ne
    1.16
    но
    1.16
    ни
    1.13
    j
    1.10
    POSITIVE LOGITS
     atvej
    1.09
    기
    1.02
    内の
    0.97
     ikut
    0.95
     iyo
    0.92
    まれた
    0.92
     agarr
    0.91
    D
    0.91
     ilmu
    0.91
     semidefinite
    0.91
    Activations Density 0.000%

    No Known Activations