© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 54022
    Prev
    Next
    INDEX
    Explanations

    say "the"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_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
    ◀
    0.37
    แนน
    0.37
    raten
    0.35
     mengen
    0.35
    ندي
    0.35
     rezat
    0.35
    웨
    0.35
    Abasis
    0.34
     инсу
    0.34
    )/\
    0.34
    POSITIVE LOGITS
     your
    0.48
     our
    0.46
     his
    0.42
    諸
    0.41
     her
    0.39
     an
    0.39
     அவற்றை
    0.39
    一支
    0.39
     marketplace
    0.38
    емые
    0.38
    Activations Density 0.005%

    No Known Activations