© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 50646
    Prev
    Next
    INDEX
    Explanations

    bathroom count in apartments

    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_31_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
    thel
    0.40
    筋
    0.40
    velyan
    0.39
    phase
    0.39
     unsol
    0.36
    堊
    0.36
    sean
    0.36
    丛
    0.35
    改装
    0.35
    씰
    0.35
    POSITIVE LOGITS
     syrup
    0.39
     nouns
    0.38
     pollinators
    0.37
     activates
    0.37
     महिलाओ
    0.36
     रुग्ण
    0.36
     retirement
    0.36
    nouns
    0.36
     मिलीमीटर
    0.35
    ক্রান্ত
    0.35
    Activations Density 0.000%

    No Known Activations