© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 203199
    Prev
    Next
    INDEX
    Explanations

    language context markers

    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_6_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
    ید
    1.30
    یر
    1.02
    ین
    0.98
    ين
    0.96
    ע
    0.96
    ו
    0.94
    and
    0.93
    ва
    0.93
    ص
    0.93
    ма
    0.92
    POSITIVE LOGITS
    1.16
    ों
    1.04
            
    0.98
    <h3>
    0.95
    <h4>
    0.89
    ring
    0.87
    s
    0.87
    ters
    0.85
     Luftwaffe
    0.85
    saus
    0.84
    Activations Density 0.000%

    No Known Activations