© 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. 165227
    Prev
    Next
    INDEX
    Explanations

    best course of action

    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
     persuasive
    0.38
    Memo
    0.38
     فريبي
    0.38
     இங்கே
    0.37
    PTH
    0.36
     (#
    0.36
    لوں
    0.35
    べき
    0.35
    Sliders
    0.35
    샥
    0.35
    POSITIVE LOGITS
     sometimes
    0.40
     certain
    0.36
     honors
    0.35
     offers
    0.35
    foods
    0.34
     নাও
    0.34
     agrees
    0.34
     gifts
    0.34
     temas
    0.34
     buys
    0.34
    Activations Density 0.003%

    No Known Activations