© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 67307
    Prev
    Next
    INDEX
    Explanations

    thermoses and insulated containers

    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_41_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
     Bishops
    0.44
    サウンド
    0.41
     Bishop
    0.39
     khawatir
    0.38
    খাল
    0.37
    桥
    0.37
     immig
    0.37
     omega
    0.36
    橋
    0.36
     alpha
    0.36
    POSITIVE LOGITS
     thermos
    1.60
     Therm
    1.52
     therm
    1.29
     thermo
    1.24
     Thermo
    1.19
    Ther
    1.17
     Flask
    1.16
     термо
    1.16
    Therm
    1.16
    Thermo
    1.15
    Activations Density 0.004%

    No Known Activations