© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 214676
    Prev
    Next
    INDEX
    Explanations

    J

    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_47_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
    Rental
    0.42
    涑
    0.42
    Dirac
    0.40
    oconut
    0.40
    btnClose
    0.40
     rectangular
    0.39
    <unused24>
    0.38
     Deposit
    0.38
     депозит
    0.38
    녕
    0.38
    POSITIVE LOGITS
    tors
    0.45
    ky
    0.43
    rot
    0.42
     jug
    0.42
    adio
    0.42
     rot
    0.41
     Port
    0.40
     bot
    0.40
     Tap
    0.40
     overtime
    0.40
    Activations Density 0.000%

    No Known Activations