© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 41502
    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_22_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
    Backspace
    0.43
     leftist
    0.42
    कारे
    0.40
     agendas
    0.40
     cetera
    0.39
     et
    0.38
    क्तिक
    0.37
    ᡵ
    0.37
    (“
    0.37
     Rainier
    0.37
    POSITIVE LOGITS
    avía
    0.43
    to
    0.42
    vat
    0.42
     d
    0.41
     firstly
    0.41
    количество
    0.40
    No
    0.39
    Мо
    0.38
    nio
    0.38
     اولا
    0.38
    Activations Density 0.000%

    No Known Activations