© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 201780
    Prev
    Next
    INDEX
    Explanations

    stakes

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     stack
    2.14
     Stack
    2.02
    Stack
    1.93
    stack
    1.88
    栈
    1.76
     stacks
    1.75
    STACK
    1.66
     stacking
    1.56
    stacks
    1.45
    棧
    1.44
    POSITIVE LOGITS
     রুমে
    0.41
    wrench
    0.41
    decade
    0.40
    winds
    0.40
    的风
    0.40
    ছো
    0.39
    worms
    0.39
    clouds
    0.38
    ग्रियों
    0.37
    鉗
    0.37
    Activations Density 0.002%

    No Known Activations