© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 76881
    Prev
    Next
    INDEX
    Explanations

    right to, right if, right case

    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_31_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
    旨
    0.40
    )(\
    0.39
    leben
    0.38
    ましい
    0.38
    ઓએ
    0.38
    lef
    0.38
     clam
    0.37
     pursuits
    0.37
     matter
    0.37
     closure
    0.37
    POSITIVE LOGITS
    timedelta
    0.40
    Fragments
    0.39
    Partial
    0.39
    }]_{
    0.39
    ∆
    0.38
    Standard
    0.38
    Supplemental
    0.37
    Primer
    0.37
    indik
    0.37
    Fitting
    0.36
    Activations Density 0.004%

    No Known Activations