© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 35974
    Prev
    Next
    INDEX
    Explanations

    improves and reduces

    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_31_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
    動き
    0.39
     propositions
    0.38
     فرض
    0.36
     Recreation
    0.36
    釜
    0.36
    conditionals
    0.36
    ucristo
    0.36
    角
    0.36
    
    0.35
     kamm
    0.35
    POSITIVE LOGITS
     balanced
    0.38
    Personality
    0.38
     processing
    0.37
    نب
    0.36
     clearest
    0.35
     amelior
    0.35
    Mental
    0.35
     digestion
    0.34
     sns
    0.34
     nn
    0.34
    Activations Density 0.018%

    No Known Activations