© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 100158
    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_14_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
    ሙሉ
    0.51
    على
    0.46
    Launching
    0.45
    Attempts
    0.45
    Т
    0.44
    ደን
    0.44
    똑
    0.43
    हेलो
    0.43
    โดย
    0.42
    rägt
    0.42
    POSITIVE LOGITS
     Voluntary
    0.52
     PROGRESS
    0.51
     sympath
    0.50
     probabilmente
    0.50
     god
    0.49
     fibrin
    0.49
     friv
    0.49
    䬲
    0.49
     partnership
    0.49
     cara
    0.49
    Activations Density 0.000%

    No Known Activations