© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 86187
    Prev
    Next
    INDEX
    Explanations

    verbs: eat, greet, am, speak, was

    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_18_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
    ี่ยว
    0.42
     themselves
    0.41
     thawing
    0.39
    Бу
    0.38
    が
    0.38
    Faucet
    0.37
    Estr
    0.37
    ն
    0.36
     picks
    0.36
    лювання
    0.36
    POSITIVE LOGITS
    oping
    0.44
    ikaner
    0.44
    urea
    0.44
    ikhil
    0.44
    ivasena
    0.43
    ulich
    0.43
     myself
    0.43
    vl
    0.42
    agger
    0.41
    larım
    0.41
    Activations Density 0.003%

    No Known Activations