© 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. 58049
    Prev
    Next
    INDEX
    Explanations

    applicants applying for jobs or services

    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
     and
    1.09
     as
    1.09
    2
    1.08
    Lite
    0.98
    KeyListener
    0.95
    ;
    0.95
    ,
    0.93
    ,【
    0.91
    ند
    0.89
    ado
    0.89
    POSITIVE LOGITS
    in
    1.51
    ع
    1.40
    ு
    1.35
    ad
    1.26
    ാ
    1.26
     a
    1.25
    ar
    1.21
    innt
    1.20
    р
    1.20
    ες
    1.19
    Activations Density 0.001%

    No Known Activations