© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 53307
    Prev
    Next
    INDEX
    Explanations

    "travelers" or "habit"

    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
     neat
    0.35
    も見
    0.33
    蝸
    0.31
     देखने
    0.30
     fascinated
    0.29
     tuttavia
    0.29
     intrigued
    0.28
    DomainMask
    0.28
     costit
    0.28
     however
    0.28
    POSITIVE LOGITS
    opl
    0.30
    '])
    0.29
    xi
    0.28
    习惯
    0.28
     казино
    0.28
    小时
    0.27
    habit
    0.27
    afon
    0.27
    либ
    0.27
    ')
    0.27
    Activations Density 0.000%

    No Known Activations