© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 161436
    Prev
    Next
    INDEX
    Explanations

    sweetie pie

    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_2_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
    るので
    1.13
    ethe
    1.11
    am
    1.10
    िशन
    1.09
    era
    1.06
    ou
    1.05
    amate
    1.02
    は
    1.01
    ின்
    1.00
    ped
    0.98
    POSITIVE LOGITS
     assassin
    1.41
     ingles
    1.20
    ગ
    1.20
     by
    1.19
     ajout
    1.18
    상
    1.17
     Ovaj
    1.16
    ટ
    1.16
    ট
    1.13
    도
    1.09
    Activations Density 0.001%

    No Known Activations