© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 167427
    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_34_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
    ritz
    0.43
     predominate
    0.38
     aspirated
    0.38
     ምንም
    0.37
    鍘
    0.36
    學院
    0.36
    먹
    0.35
    强化
    0.35
     pumped
    0.34
    ורי
    0.34
    POSITIVE LOGITS
     if
    0.64
     если
    0.62
     якщо
    0.58
     إذا
    0.57
     hvis
    0.54
     If
    0.53
     jika
    0.53
     nếu
    0.53
    если
    0.50
    If
    0.50
    Activations Density 0.000%

    No Known Activations