© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 235159
    Prev
    Next
    INDEX
    Explanations

    going

    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
    भौ
    0.40
    MUST
    0.39
     тяж
    0.38
    must
    0.37
    leduj
    0.36
    строй
    0.36
    ⓔ
    0.36
    燚
    0.35
    рный
    0.35
    প্র
    0.34
    POSITIVE LOGITS
     Faraday
    0.43
     வழக்கு
    0.39
     CDS
    0.38
    ណ្ត
    0.37
     Wart
    0.37
     flusso
    0.36
    Symbols
    0.36
    visional
    0.35
     contention
    0.34
     IZ
    0.34
    Activations Density 0.001%

    No Known Activations