© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 150274
    Prev
    Next
    INDEX
    Explanations

    DEM scenes

    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_60_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
    i
    0.44
    u
    0.39
     wearer
    0.38
    şi
    0.36
    ட்டும்
    0.35
     armband
    0.35
    گر
    0.35
    adze
    0.34
     $:=$
    0.34
    łki
    0.34
    POSITIVE LOGITS
     Scene
    0.65
    dem
    0.64
    land
    0.60
     dem
    0.60
     DEM
    0.59
     producto
    0.58
     Dem
    0.57
    Dem
    0.57
    DEM
    0.57
     Scenes
    0.56
    Activations Density 0.001%

    No Known Activations