© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 167600
    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_34_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
     pü
    0.43
     बल्लेबाजी
    0.38
     профессии
    0.38
     مان
    0.38
     getUsers
    0.38
     posteriori
    0.38
    𒇷
    0.37
    椹
    0.37
    从未
    0.36
    勐
    0.36
    POSITIVE LOGITS
    Mon
    0.41
    Bennett
    0.38
     معاد
    0.37
    Compare
    0.37
     Virol
    0.37
     ск
    0.36
    yeri
    0.36
    Str
    0.35
    Ku
    0.34
     TRIG
    0.34
    Activations Density 0.000%

    No Known Activations