© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 155812
    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_50_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
    鉱
    0.39
     марта
    0.37
    krieg
    0.36
    끔
    0.36
    ক্ষণ
    0.35
    --)
    0.35
    igten
    0.35
     प्रे
    0.35
    }^{*},
    0.34
    monton
    0.34
    POSITIVE LOGITS
    يال
    0.46
     rb
    0.44
     HB
    0.42
    hbs
    0.42
     fo
    0.42
     FBS
    0.41
     Fq
    0.41
     hb
    0.40
     Rb
    0.40
     Clio
    0.40
    Activations Density 0.000%

    No Known Activations