© 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. 236457
    Prev
    Next
    INDEX
    Explanations

    robots manipulation

    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
    腰
    0.40
     movimenti
    0.39
    imiya
    0.39
    ukat
    0.38
     cvec
    0.37
    Milk
    0.36
     kne
    0.36
     विवेकानंद
    0.36
    కో
    0.36
     adul
    0.35
    POSITIVE LOGITS
     Setting
    0.42
     설정
    0.42
     setting
    0.40
    设定
    0.39
    Setting
    0.38
     R
    0.38
    QD
    0.38
    ITICAL
    0.37
    ezas
    0.37
    R
    0.37
    Activations Density 0.002%

    No Known Activations