© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 193802
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_27_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
     schul
    0.44
     öffentlich
    0.42
     enigma
    0.41
     reto
    0.40
     공개
    0.39
     найбіль
    0.39
    㳒
    0.39
    ារ
    0.39
     не
    0.38
    ิด
    0.38
    POSITIVE LOGITS
     preserves
    0.38
    yl
    0.38
    slider
    0.36
    қу
    0.36
    left
    0.35
    ท่องเที่ยว
    0.35
     Preserve
    0.35
    éi
    0.35
     left
    0.35
    ocycl
    0.34
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.