© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 193745
    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_4_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
    ک
    0.55
     आए
    0.53
     Davao
    0.51
     suatu
    0.51
    MAGIC
    0.51
    काब
    0.50
     हाम्रो
    0.50
    kj
    0.50
     asing
    0.50
     одного
    0.49
    POSITIVE LOGITS
    t
    0.46
     quatre
    0.40
     personal
    0.39
    ↵↵
    0.39
    urn
    0.39
    ton
    0.38
    util
    0.38
     personnal
    0.38
     পিতাম
    0.37
    elt
    0.37
    Activations Density 0.000%

    No Known Activations