© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 15685
    Prev
    Next
    INDEX
    Explanations

    positioning and alignment

    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_34_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
     Generally
    0.38
     sprinkles
    0.38
    ക്കുകയും
    0.37
    Flow
    0.36
    कृष्ण
    0.36
     सब्
    0.35
    నుక
    0.35
    詎
    0.35
    Generally
    0.35
    吟
    0.35
    POSITIVE LOGITS
    접
    0.39
    rieg
    0.38
    intel
    0.36
    uders
    0.35
    Listener
    0.34
     Tex
    0.34
     JAMES
    0.34
    cass
    0.34
     Listener
    0.34
    ieso
    0.34
    Activations Density 0.027%

    No Known Activations