© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 87155
    Prev
    Next
    INDEX
    Explanations

    denormalization, dendrogram, Hague

    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_3_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
    ed
    0.62
    ogenous
    0.58
    ının
    0.55
    asını
    0.54
    iov
    0.53
    esar
    0.53
    ↵
    0.53
     використову
    0.52
     demurrer
    0.52
    ną
    0.51
    POSITIVE LOGITS
    ン
    0.77
    ရင်း
    0.75
    ка
    0.68
    ته
    0.68
    н
    0.68
    र्थिक
    0.65
    ہ
    0.62
    ז
    0.62
    vény
    0.61
    )
    0.61
    Activations Density 0.000%

    No Known Activations