© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 66768
    Prev
    Next
    INDEX
    Explanations

    visual studio marketplace item names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_41_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
    篪
    0.41
    हाबाद
    0.40
    ચે
    0.40
    chea
    0.39
     restorative
    0.38
     CASCADE
    0.38
     대상
    0.37
    
    0.36
    cparam
    0.36
     Syntax
    0.36
    POSITIVE LOGITS
    Alf
    0.43
     custom
    0.40
    Support
    0.38
    IOT
    0.38
    go
    0.38
     Blum
    0.38
     Support
    0.38
    quinone
    0.37
    Custom
    0.37
     Luigi
    0.36
    Activations Density 0.000%

    No Known Activations