© 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. 120901
    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
     universality
    0.35
    Է
    0.34
    리어
    0.33
    િલ્
    0.32
    Malay
    0.32
     Rais
    0.31
     vow
    0.30
    ଲ
    0.30
    اث
    0.30
     competitively
    0.30
    POSITIVE LOGITS
    㥆
    0.38
    uya
    0.38
     potro
    0.37
     trasera
    0.37
     түр
    0.36
    brochen
    0.36
     বিরত
    0.36
    penas
    0.35
    ष्‍ट्र
    0.35
    mockito
    0.34
    Activations Density 0.000%

    No Known Activations