© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 195360
    Prev
    Next
    INDEX
    Explanations

    SMILES chemical notation

    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_27_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
    лли
    0.48
    攙
    0.40
    νοντας
    0.40
    🦯
    0.40
    㫧
    0.40
    вает
    0.40
     różnych
    0.39
     variés
    0.39
    㚐
    0.39
     durée
    0.38
    POSITIVE LOGITS
    percent
    0.43
     Beat
    0.41
     Conserv
    0.41
     Percent
    0.40
    5
    0.40
    year
    0.40
    attr
    0.39
    beat
    0.39
     кан
    0.38
    aap
    0.38
    Activations Density 0.001%

    No Known Activations