© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 150479
    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_23_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
    "
    0.50
     meaning
    0.43
     get
    0.41
     Ranges
    0.40
     breaking
    0.39
     گر
    0.38
     Breaking
    0.38
     قط
    0.38
    獲
    0.38
     running
    0.38
    POSITIVE LOGITS
    𒆪
    0.52
    adə
    0.49
     retorted
    0.48
    াতিক
    0.47
     ఆరోగ్య
    0.46
    malıdır
    0.46
    uticas
    0.45
     जड़
    0.45
    utilisateur
    0.44
     आसमान
    0.44
    Activations Density 0.000%

    No Known Activations