© 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. 80126
    Prev
    Next
    INDEX
    Explanations

    'r' followed by quote

    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
     സോഷ്യ
    0.40
     aislado
    0.38
     القرن
    0.38
     sociales
    0.37
    রিত
    0.37
     Bulletin
    0.36
     कट्टर
    0.36
    |^{\
    0.36
    မ
    0.35
     Negotiation
    0.35
    POSITIVE LOGITS
    kk
    0.42
     inlet
    0.41
    kw
    0.41
     essentially
    0.40
    essentially
    0.38
    hk
    0.38
    planetary
    0.38
     inlets
    0.38
    accam
    0.37
     خلي
    0.37
    Activations Density 0.000%

    No Known Activations