© 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. 170285
    Prev
    Next
    INDEX
    Explanations

    person performing action

    np_max-act-logits · gemini-2.5-flash-lite
    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
     loving
    0.45
    털
    0.38
    mények
    0.38
    loving
    0.37
    Loving
    0.37
    訣
    0.37
     having
    0.36
    might
    0.36
    િયાન
    0.36
     좌
    0.36
    POSITIVE LOGITS
     loves
    0.62
     listens
    0.61
     tries
    0.59
     learns
    0.54
    next
    0.54
     next
    0.53
     swims
    0.52
     sadly
    0.51
     reaches
    0.51
     Next
    0.50
    Activations Density 0.007%

    No Known Activations