© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 88771
    Prev
    Next
    INDEX
    Explanations

    I say

    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_23_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
     biasanya
    0.41
    র্ষি
    0.41
    ندہ
    0.40
    Ꮸ
    0.40
    ucidation
    0.38
    alaikums
    0.38
    𝙷
    0.38
    ्यूट
    0.37
     modeled
    0.37
    靛
    0.37
    POSITIVE LOGITS
    อย่างไร
    0.36
     Joshua
    0.35
     %
    0.35
     overall
    0.35
     lā
    0.33
     diminutive
    0.33
    artney
    0.33
     \%$
    0.32
     o
    0.32
    任意
    0.32
    Activations Density 0.034%

    No Known Activations