© 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. 161402
    Prev
    Next
    INDEX
    Explanations

    yogurt soup or parfait

    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
     be
    1.99
     I
    1.49
     are
    1.31
     d
    1.27
     S
    1.26
     P
    1.23
     e
    1.22
     V
    1.20
     s
    1.20
     D
    1.20
    POSITIVE LOGITS
     aplatis
    1.33
     indiquer
    1.31
     arrondie
    1.25
     ajout
    1.24
     attaqu
    1.23
     remport
    1.23
     spéciale
    1.20
     âg
    1.18
    baiki
    1.16
     pointillés
    1.16
    Activations Density 0.000%

    No Known Activations