© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 51912
    Prev
    Next
    INDEX
    Explanations

    different or another

    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
     heur
    0.38
    currentTime
    0.36
    खून
    0.34
    രള
    0.34
     $€
    0.34
    їн
    0.33
    รัฐ
    0.33
    дук
    0.33
    牪
    0.33
     '".$
    0.33
    POSITIVE LOGITS
     different
    0.72
     another
    0.71
     Different
    0.66
    different
    0.66
     diferente
    0.65
     diferentes
    0.63
    another
    0.63
    Different
    0.62
     Another
    0.61
    不同的
    0.59
    Activations Density 0.044%

    No Known Activations