© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159666
    Prev
    Next
    INDEX
    Explanations

    besties, -ies, -s ending

    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
     in
    1.27
    える
    1.23
     enfoc
    0.99
    ও
    0.96
     aplic
    0.94
    在
    0.93
    !
    0.93
    Š
    0.90
    I
    0.90
    PRE
    0.86
    POSITIVE LOGITS
    is
    1.56
    are
    1.40
    as
    1.38
    ere
    1.04
    akn
    1.02
    an
    1.02
    il
    0.99
    ه
    0.98
    ak
    0.97
    has
    0.97
    Activations Density 0.001%

    No Known Activations