© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 32094
    Prev
    Next
    INDEX
    Explanations

    data analysis, statistics, metrics

    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_31_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
     Pengembangan
    0.38
    𝓟
    0.37
     Desmond
    0.36
    ulatus
    0.36
    čiť
    0.36
    uyết
    0.35
     Garr
    0.35
     Entwicklung
    0.35
     середи
    0.34
    枻
    0.34
    POSITIVE LOGITS
     거지
    0.41
     voltages
    0.41
     score
    0.38
     voltage
    0.38
    reactions
    0.36
     scores
    0.36
     analyst
    0.36
     حدا
    0.35
    yearly
    0.35
    voltage
    0.34
    Activations Density 0.128%

    No Known Activations