© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 88906
    Prev
    Next
    INDEX
    Explanations

    inet

    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
    ↵
    0.98
    in
    0.81
     experienced
    0.67
    </h2>
    0.66
    ಊ
    0.66
    ַ
    0.66
     도시
    0.64
     seguenti
    0.64
     unpre
    0.63
    ׳
    0.63
    POSITIVE LOGITS
    .
    1.12
    0.88
    EN
    0.83
    CK
    0.80
    ü
    0.80
    ET
    0.77
    ol
    0.75
    MAN
    0.75
    S
    0.75
    .…
    0.74
    Activations Density 0.000%

    No Known Activations