© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 141430
    Prev
    Next
    INDEX
    Explanations

    boost / experience

    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_46_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
    }`))
    0.39
     sapien
    0.38
     storey
    0.37
     Öğ
    0.37
    ຂອງ
    0.36
    iena
    0.36
    ຕ່
    0.36
     pancre
    0.36
     Nich
    0.35
     Expression
    0.35
    POSITIVE LOGITS
     scooped
    0.45
     F
    0.45
     boosted
    0.42
    boost
    0.40
    Info
    0.39
    Lin
    0.38
     boosts
    0.38
     EXPERIENCE
    0.38
    Boost
    0.37
    Beef
    0.36
    Activations Density 0.000%

    No Known Activations