© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 194679
    Prev
    Next
    INDEX
    Explanations

    a bit

    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_15_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
     liés
    0.29
    ^{\
    0.29
     associés
    0.28
     relação
    0.26
    )^{\
    0.26
     Tun
    0.26
    families
    0.26
     deseos
    0.25
     liées
    0.25
    ություններ
    0.25
    POSITIVE LOGITS
    ed
    0.25
     Beast
    0.24
    handlung
    0.23
    الك
    0.23
    cast
    0.22
    y
    0.22
    adə
    0.22
    പ
    0.22
    𝘤
    0.22
    вець
    0.22
    Activations Density 0.025%

    No Known Activations