© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 124893
    Prev
    Next
    INDEX
    Explanations

    bedrooms or bathrooms

    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_3_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
    és
    0.68
    ارك
    0.62
     e
    0.61
     stehen
    0.61
    anze
    0.59
    ل
    0.58
     bekommen
    0.58
     n
    0.57
     jedem
    0.57
    atanga
    0.56
    POSITIVE LOGITS
    N
    0.89
    B
    0.84
    D
    0.79
    J
    0.76
    G
    0.75
    the
    0.73
    K
    0.73
    ;
    0.71
    H
    0.71
    S
    0.71
    Activations Density 0.000%

    No Known Activations