© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 198953
    Prev
    Next
    INDEX
    Explanations

    company names

    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_50_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
     Laser
    0.43
     Daisy
    0.42
     Ras
    0.41
    ಭಾ
    0.41
     ລ
    0.39
     Mouse
    0.39
     ense
    0.39
     Las
    0.39
     Lip
    0.39
     Moshe
    0.39
    POSITIVE LOGITS
    Kem
    0.40
    вок
    0.39
     HomeComponent
    0.39
     달
    0.38
    芡
    0.37
    역
    0.37
    CCCN
    0.37
     longiore
    0.37
    プレミアム
    0.37
     Novartis
    0.37
    Activations Density 0.001%

    No Known Activations