© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 39777
    Prev
    Next
    INDEX
    Explanations

    feeling disconnected or hollow

    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_11_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
     $\
    0.67
    もら
    0.57
    も
    0.57
    ați
    0.56
     $^{
    0.54
     can
    0.51
     $(*
    0.51
    verd
    0.50
     \
    0.50
                                   
    0.50
    POSITIVE LOGITS
    RA
    0.54
    FN
    0.53
    éries
    0.51
     vuoden
    0.50
    PDM
    0.50
    Reve
    0.50
     diarios
    0.50
    ၂
    0.50
    DE
    0.50
    SEL
    0.49
    Activations Density 0.016%

    No Known Activations