© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 134280
    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_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
    ج
    1.13
    お金
    0.99
    㓞
    0.89
    "
    0.89
    cción
    0.89
    ق
    0.88
    स
    0.87
     It
    0.85
    tiin
    0.85
    䖝
    0.85
    POSITIVE LOGITS
    8
    1.41
    7
    1.38
    6
    1.30
    3
    1.29
    about
    1.22
    ה
    1.20
    5
    1.13
    ৩
    1.13
     about
    1.06
     indah
    1.03
    Activations Density 0.000%

    No Known Activations