© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 2705
    Prev
    Next
    INDEX
    Explanations

    said/spoke

    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_44_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
    λά
    0.40
    PICK
    0.38
    珅
    0.37
     azok
    0.37
    اهد
    0.36
     base
    0.35
    antiation
    0.35
    ेल
    0.35
    ंची
    0.34
    earch
    0.34
    POSITIVE LOGITS
     breathed
    0.47
     said
    0.43
     thở
    0.43
     breathe
    0.41
    ఊ
    0.38
     తే
    0.38
     Fabrication
    0.38
     Breath
    0.38
     breathes
    0.37
    Said
    0.37
    Activations Density 0.010%

    No Known Activations