© 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
    2. Gemma-3-27B-IT
    3. 23-GEMMASCOPE-2-TRANSCODER-262K
    4. 87100
    Prev
    Next
    INDEX
    Explanations

    python, react, js, spring

    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_23_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
    可用
    0.45
    Opportun
    0.43
    Wildlife
    0.42
     objeto
    0.41
     Pét
    0.40
     менедж
    0.39
     giá
    0.39
    暾
    0.38
     pulverized
    0.38
     oggetto
    0.38
    POSITIVE LOGITS
    pair
    0.41
    oral
    0.40
    assist
    0.40
    upid
    0.40
    apte
    0.39
    spatial
    0.38
    nie
    0.38
    astes
    0.37
    relatively
    0.37
    """,
    0.37
    Activations Density 0.024%

    No Known Activations