© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 203207
    Prev
    Next
    INDEX
    Explanations

    influence, gifts

    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_46_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
     expérience
    0.43
    clusión
    0.41
     నిర్మా
    0.39
    antages
    0.38
     Experience
    0.37
    expérience
    0.37
    ንሽ
    0.37
    㹮
    0.37
    aranteed
    0.37
    ভূতির
    0.37
    POSITIVE LOGITS
     influence
    0.59
    influence
    0.47
    gifts
    0.47
     Influence
    0.46
    Influence
    0.46
     influences
    0.46
     gifts
    0.46
    engaruhi
    0.46
    礼物
    0.44
     παρου
    0.44
    Activations Density 0.006%

    No Known Activations