© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 43076
    Prev
    Next
    INDEX
    Explanations

    oil production levels

    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_13_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
    dr
    0.73
    v
    0.70
    1
    0.61
     us
    0.60
    nt
    0.59
    DR
    0.56
     not
    0.55
    words
    0.53
    н
    0.52
     words
    0.52
    POSITIVE LOGITS
     Existem
    0.62
    jelasan
    0.59
    వలం
    0.58
     मिलाकर
    0.57
     ของ
    0.56
     Onun
    0.55
    ต่
    0.55
    <unused583>
    0.54
    祹
    0.53
     Ombudsman
    0.52
    Activations Density 0.004%

    No Known Activations