© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 121363
    Prev
    Next
    INDEX
    Explanations

    variable assignment and calculation

    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_27_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
    代的
    0.36
     태
    0.36
     photosynthesis
    0.35
    ängen
    0.35
    ijev
    0.34
     таки
    0.34
     제품
    0.34
    湟
    0.34
    醎
    0.33
    ając
    0.33
    POSITIVE LOGITS
     monies
    0.37
    三天
    0.36
     parabolic
    0.35
    സ്സ
    0.34
    டிக்கும்
    0.34
    फाली
    0.34
     spanned
    0.33
     سٹی
    0.33
    ಹಿತ
    0.32
     infallible
    0.31
    Activations Density 0.000%

    No Known Activations