© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 204994
    Prev
    Next
    INDEX
    Explanations

    them to

    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_25_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
     स्थापित
    0.43
     completos
    0.41
     primeiros
    0.39
    劳
    0.36
     achie
    0.36
    ologisk
    0.36
    шив
    0.36
    Fermi
    0.35
     estabele
    0.35
    ุต
    0.35
    POSITIVE LOGITS
     shading
    0.41
     braces
    0.40
    brace
    0.38
     distressing
    0.38
     acá
    0.37
    いますが
    0.37
     Coating
    0.37
     Nana
    0.37
    ],
    0.36
    dragging
    0.36
    Activations Density 0.005%

    No Known Activations