© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 86566
    Prev
    Next
    INDEX
    Explanations

    API calls

    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
     aureus
    0.35
     wenn
    0.34
    ḥ
    0.34
     press
    0.32
    erevan
    0.32
    ņ
    0.32
    Bench
    0.32
     dues
    0.32
    λευ
    0.32
     à
    0.32
    POSITIVE LOGITS
    㘿
    0.40
    TextAlign
    0.37
    よそ
    0.37
     ظاهر
    0.37
    𝗞
    0.37
    োলজি
    0.36
    aterData
    0.36
     फॉलोइंग
    0.36
     நோக்க
    0.35
    zecz
    0.35
    Activations Density 0.002%

    No Known Activations