© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 204935
    Prev
    Next
    INDEX
    Explanations

    3

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    ՝
    0.38
    пер
    0.37
     italy
    0.36
    
    0.35
     Cut
    0.35
     Arth
    0.35
     Sinon
    0.34
    —
    0.34
    ־
    0.34
     largo
    0.34
    POSITIVE LOGITS
    A
    0.52
    ාව
    0.45
    Transit
    0.45
    bcc
    0.41
    phony
    0.41
    cF
    0.41
    একে
    0.40
    ª
    0.40
    pF
    0.40
    AO
    0.40
    Activations Density 0.001%

    No Known Activations