© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 110648
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_2_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
    ר
    2.02
    ت
    1.69
     for
    1.63
    ه
    1.56
    ה
    1.55
    -
    1.49
    고
    1.49
    ת
    1.45
    t
    1.41
    ৫
    1.41
    POSITIVE LOGITS
    ामध्ये
    1.23
    ным
    1.14
     in
    1.08
     जिसके
    1.05
     hvilket
    1.04
    ков
    1.03
    op
    1.02
    いますが
    0.99
     ਅਤੇ
    0.98
     οποίο
    0.97
    Activations Density 0.000%

    No Known Activations