© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 137168
    Prev
    Next
    INDEX
    Explanations

    subscription boxes

    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_12_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
    را
    0.65
     tetr
    0.51
    اا
    0.48
    
    0.48
    با
    0.48
    Broadway
    0.48
     زی
    0.48
    രം
    0.47
    Mumbai
    0.47
    Hazard
    0.47
    POSITIVE LOGITS
    arnas
    0.51
    folge
    0.47
    q
    0.46
     regimes
    0.45
     subscription
    0.45
     Estos
    0.45
     Tee
    0.44
     Subscription
    0.44
     hatte
    0.44
     estuvieron
    0.44
    Activations Density 0.001%

    No Known Activations