© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 61871
    Prev
    Next
    INDEX
    Explanations

    entering or examination

    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_11_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
    ni
    0.65
    0.64
    la
    0.63
    なので
    0.61
     Models
    0.61
     Update
    0.58
     i
    0.56
     R
    0.54
     Cr
    0.54
     Engineering
    0.54
    POSITIVE LOGITS
     특정
    0.58
     კომპ
    0.55
     miscon
    0.55
    homogeneous
    0.55
     medallions
    0.54
    Ꮭ
    0.54
    usst
    0.54
     burgundy
    0.53
    javaHome
    0.53
    ılığı
    0.53
    Activations Density 0.000%

    No Known Activations