© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 34886
    Prev
    Next
    INDEX
    Explanations

    oil tanker

    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_3_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
    ление
    0.73
    ے
    0.71
     caring
    0.69
     incandescent
    0.69
    𝘦
    0.68
    ৩৪
    0.66
    ers
    0.66
    าร
    0.65
    1
    0.64
     inert
    0.63
    POSITIVE LOGITS
    k
    1.13
    w
    0.88
    ك
    0.86
    n
    0.84
    را
    0.84
    ي
    0.83
    x
    0.81
    b
    0.80
    ча
    0.80
    IA
    0.79
    Activations Density 0.010%

    No Known Activations