© 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
    2. Gemma-3-27B-IT
    3. 34-GEMMASCOPE-2-TRANSCODER-262K
    4. 16118
    Prev
    Next
    INDEX
    Explanations

    dictionary keys and values

    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
    粔
    0.39
    ondi
    0.37
    ikor
    0.36
    राने
    0.36
     সিলেটের
    0.36
     pati
    0.35
     کلی
    0.35
    ψει
    0.35
     enterprise
    0.35
     bagaimana
    0.35
    POSITIVE LOGITS
    "":
    0.41
     straightened
    0.40
     confesses
    0.39
     "#
    0.39
     ramps
    0.39
     "{
    0.38
     confess
    0.38
    ruv
    0.38
    र्मेंद्र
    0.37
     "[
    0.36
    Activations Density 0.086%

    No Known Activations