© 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. 152906
    Prev
    Next
    INDEX
    Explanations

    HTML entities

    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
     regener
    0.41
     regenerate
    0.40
    Clo
    0.40
    颛
    0.39
     deductible
    0.39
     immersion
    0.38
     clo
    0.38
     immerse
    0.37
     soluble
    0.37
     revitalize
    0.37
    POSITIVE LOGITS
     আমার
    0.39
     দেখলে
    0.37
    要因
    0.36
     Rotten
    0.35
    ]:
    0.35
     отдельных
    0.34
    -])
    0.33
    行为
    0.32
     বললে
    0.32
     phong
    0.32
    Activations Density 0.003%

    No Known Activations