© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 1244
    Prev
    Next
    INDEX
    Explanations

    us, usa

    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_44_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
     carbur
    0.43
     HAC
    0.43
     namik
    0.41
     तीस
    0.39
    按
    0.39
    tch
    0.38
     Paragu
    0.38
     interrupt
    0.37
     Smart
    0.37
     afterthought
    0.37
    POSITIVE LOGITS
    ائن
    0.39
    slideDuplicate
    0.38
     latar
    0.36
    REMOVE
    0.36
    രീ
    0.35
     nodeId
    0.35
    ఓ
    0.35
    áva
    0.35
    గం
    0.35
    anlı
    0.35
    Activations Density 0.004%

    No Known Activations