© 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. 227814
    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
    :
    0.96
    el
    0.93
    𝐓
    0.80
    ’
    0.77
     effectuées
    0.77
    mma
    0.76
    vf
    0.76
    辶
    0.76
    Το
    0.75
    సూరు
    0.74
    POSITIVE LOGITS
     was
    1.00
    ים
    0.94
    ä
    0.91
     not
    0.85
    s
    0.84
    یس
    0.82
    ید
    0.80
    ی
    0.79
    ة
    0.77
    ा
    0.75
    Activations Density 0.000%

    No Known Activations