© 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. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 212196
    Prev
    Next
    INDEX
    Explanations

    old computer specs

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_43_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
     Altos
    0.41
    sting
    0.39
    axes
    0.39
     stry
    0.39
    ">=
    0.38
    Deployment
    0.38
     Connolly
    0.38
    Watts
    0.38
    tsx
    0.37
    抽
    0.37
    POSITIVE LOGITS
     aliquam
    0.40
     давно
    0.38
    ⒉
    0.38
     फैस
    0.37
    裱
    0.37
    rafish
    0.36
     warmth
    0.35
     dritten
    0.35
     darken
    0.35
     প্রদান
    0.35
    Activations Density 0.003%

    No Known Activations