© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 132280
    Prev
    Next
    INDEX
    Explanations

    changes or alterations

    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_1_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
    م
    1.43
    ك
    1.41
    м
    1.10
    كد
    1.09
    ка
    1.05
    ربي
    1.02
    ري
    1.00
    كار
    1.00
    كس
    0.99
    1
    0.99
    POSITIVE LOGITS
    ing
    1.10
    -
    0.96
    "
    0.96
    िंग
    0.84
    見
    0.82
    ines
    0.80
    ando
    0.79
    ase
    0.77
    valence
    0.75
    inde
    0.75
    Activations Density 0.004%

    No Known Activations