© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 200829
    Prev
    Next
    INDEX
    Explanations

    bet

    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_46_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
     Very
    0.41
     muy
    0.39
     LinkedIn
    0.38
    玄
    0.38
     Query
    0.37
    şil
    0.37
     Ge
    0.37
    ologii
    0.37
     Maz
    0.36
     Santana
    0.36
    POSITIVE LOGITS
    돈
    0.50
     moneys
    0.47
     money
    0.47
     dinheiro
    0.45
     denaro
    0.44
    现金
    0.43
    geld
    0.43
     apex
    0.42
    भाव
    0.41
     पैसों
    0.41
    Activations Density 0.000%

    No Known Activations