© 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. 110248
    Prev
    Next
    INDEX
    Explanations

    defies expectations

    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
    a
    1.74
    an
    1.51
    on
    1.46
    as
    1.38
    다
    1.36
    া
    1.27
    en
    1.26
    in
    1.25
    um
    1.23
    <0x0D>
    1.21
    POSITIVE LOGITS
     líquido
    1.12
    ла
    1.09
     usado
    1.05
     سي
    1.03
     arbre
    1.03
     personalizado
    1.02
     =
    1.02
     usando
    1.02
     común
    1.01
     persoane
    1.01
    Activations Density 0.000%

    No Known Activations