© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 8545
    Prev
    Next
    INDEX
    Explanations

    private balcony, multiple pools, City View

    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_40_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
    uers
    0.37
     createTask
    0.35
    領域
    0.35
     metamorphosis
    0.35
     पोली
    0.35
     metamorphic
    0.35
    íf
    0.35
    声
    0.34
    otification
    0.33
     polyt
    0.33
    POSITIVE LOGITS
     furnished
    0.70
     Furn
    0.61
    furnished
    0.59
    Furn
    0.59
     furnishing
    0.53
     furnish
    0.49
    furn
    0.41
     furn
    0.41
     furnishes
    0.41
    限量
    0.40
    Activations Density 0.011%

    No Known Activations