© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 35629
    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_31_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
     pide
    0.39
     AVC
    0.38
     HSV
    0.37
    廂
    0.37
    曜
    0.36
     착
    0.36
     nabí
    0.36
    뎀
    0.36
     qualifies
    0.36
     lube
    0.36
    POSITIVE LOGITS
     vegetarian
    0.38
    сно
    0.36
     dawa
    0.35
    ັດ
    0.35
    listen
    0.35
    нете
    0.34
     институт
    0.34
    центра
    0.34
    }")]
    0.33
    ત્રી
    0.33
    Activations Density 0.000%

    No Known Activations