© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 14472
    Prev
    Next
    INDEX
    Explanations

    souvenirs and gifts

    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_34_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
     Raleigh
    0.37
    рэ
    0.37
     dean
    0.37
    FieldContext
    0.35
    ОВА
    0.35
    oine
    0.35
     المطلوب
    0.35
    举
    0.34
    GroupLayout
    0.34
    Dean
    0.34
    POSITIVE LOGITS
     artifacts
    0.70
     memorabilia
    0.64
     artefacts
    0.64
     பொருட்கள்
    0.60
    artifacts
    0.60
     paraphernalia
    0.59
     items
    0.57
     merchandise
    0.57
     souvenirs
    0.56
     Artifact
    0.55
    Activations Density 0.069%

    No Known Activations