© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 216093
    Prev
    Next
    INDEX
    Explanations

    property ownership and state

    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
    тура
    0.38
     края
    0.38
    Joining
    0.36
    Encript
    0.36
    怼
    0.36
    ја
    0.35
    Requirements
    0.35
    变的
    0.35
     Afghanistan
    0.34
    ктора
    0.34
    POSITIVE LOGITS
     repairs
    0.48
     clogged
    0.45
     mortgages
    0.43
     Repairs
    0.42
     repair
    0.42
    贷
    0.42
     mortgage
    0.41
    blurred
    0.41
     flips
    0.41
    bett
    0.40
    Activations Density 0.001%

    No Known Activations