© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 140603
    Prev
    Next
    INDEX
    Explanations

    Hollywood Hop

    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
     বিস্ফ
    0.40
    芑
    0.40
     deportivos
    0.40
     referencia
    0.40
    াস্থ্যের
    0.40
    𓍊
    0.39
     cricketers
    0.39
    रविवार
    0.39
     বিনষ্ট
    0.38
     रिलेशन
    0.38
    POSITIVE LOGITS
     T
    0.47
     Hank
    0.42
    тке
    0.41
     ac
    0.39
    near
    0.39
    T
    0.39
     near
    0.38
     Call
    0.37
     Nos
    0.37
     Unis
    0.37
    Activations Density 0.000%

    No Known Activations