© 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. 199182
    Prev
    Next
    INDEX
    Explanations

    Penrose stairs, parents, ibis, Aeronautics

    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
     ability
    0.53
     in
    0.48
     Crank
    0.46
    abilir
    0.45
     inline
    0.45
     isn
    0.44
     eingeb
    0.44
     f
    0.44
    ualitas
    0.44
     kvalitet
    0.44
    POSITIVE LOGITS
    ကျော်
    0.51
    නා
    0.48
    చన
    0.47
    郗
    0.47
    Virgin
    0.47
    ścia
    0.47
     ٹرسٹ
    0.47
     Administração
    0.46
    𝐴
    0.46
    үнд
    0.46
    Activations Density 0.000%

    No Known Activations