© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 33943
    Prev
    Next
    INDEX
    Explanations

    impenetrable, impressing, impassable, implying

    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_7_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
    a
    0.61
    ∈</
    0.61
    ("")
    0.59
    r
    0.55
    G
    0.54
          
    0.54
              
    0.54
    ı
    0.53
     indépend
    0.52
    uldig
    0.51
    POSITIVE LOGITS
     consoles
    0.55
     laboratories
    0.53
     exámenes
    0.53
    ता
    0.52
    ricos
    0.51
     élèves
    0.51
     cabling
    0.51
     cables
    0.50
     examiners
    0.50
    ಜ್ಜ
    0.50
    Activations Density 0.000%

    No Known Activations