© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 207308
    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_56_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
     있으
    0.40
    '):
    0.40
     Continue
    0.37
    Continue
    0.37
     dê
    0.37
    èg
    0.36
     général
    0.35
     disappeared
    0.35
     ক
    0.35
    .');
    0.34
    POSITIVE LOGITS
    tor
    0.41
    cards
    0.40
     Off
    0.39
    reload
    0.38
    olas
    0.38
    down
    0.37
    downs
    0.37
    yanka
    0.35
    PAT
    0.34
     DOWN
    0.34
    Activations Density 0.000%

    No Known Activations