© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 219182
    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
    ን
    0.40
    NELL
    0.39
    imala
    0.38
    ChooseCharacter
    0.38
    esercizio
    0.38
    nuget
    0.38
    erial
    0.37
    ouncements
    0.37
     exercise
    0.36
    Cancel
    0.36
    POSITIVE LOGITS
     originates
    0.40
    粞
    0.37
    োর্
    0.36
     shading
    0.36
     inscriptions
    0.36
     mauris
    0.36
     midfield
    0.33
    証明
    0.32
     কোথ
    0.32
     Storm
    0.32
    Activations Density 0.000%

    No Known Activations