© 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. 40948
    Prev
    Next
    INDEX
    Explanations

    melting, crucible, electrode, tube

    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
    "。
    0.53
     دانش
    0.51
    𝘴
    0.51
     unequiv
    0.50
    ка
    0.50
     ಕರೆ
    0.50
    ଲେ
    0.50
     දු
    0.49
    /}{
    0.49
    休息
    0.48
    POSITIVE LOGITS
     .
    0.57
     ,
    0.55
     e
    0.49
     אפ
    0.49
     demol
    0.48
     \
    0.47
     ruby
    0.46
     Reno
    0.45
     demolish
    0.45
     metal
    0.45
    Activations Density 0.030%

    No Known Activations