© 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
    2. Gemma-3-27B-IT
    3. 11-GEMMASCOPE-2-TRANSCODER-262K
    4. 61859
    Prev
    Next
    INDEX
    Explanations

    wondering about

    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_11_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
     alleviating
    0.67
     offend
    0.65
     它
    0.65
    嫐
    0.65
     बीच
    0.65
     Orrell
    0.64
     incidente
    0.63
    ELINE
    0.63
    竑
    0.63
    腚
    0.63
    POSITIVE LOGITS
    ut
    0.79
    ра
    0.73
    е
    0.68
    0
    0.66
    ip
    0.61
    жу
    0.60
    ча
    0.59
    ܙ
    0.59
    ید
    0.58
    )،
    0.58
    Activations Density 0.000%

    No Known Activations