© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 35097
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_7_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
    .
    0.85
    sa
    0.81
    tor
    0.80
    tl
    0.74
    .<
    0.72
    dan
    0.71
    di
    0.71
     n
    0.71
    si
    0.71
     h
    0.70
    POSITIVE LOGITS
     atvej
    0.69
    ৩
    0.69
    기
    0.67
     concom
    0.65
    ﺎ
    0.63
    Д
    0.61
    μού
    0.59
     constancy
    0.59
     màu
    0.58
    ત્રો
    0.58
    Activations Density 0.000%

    No Known Activations