© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 168556
    Prev
    Next
    INDEX
    Explanations

    should or can

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    :"
    0.43
     light
    0.41
    :"+
    0.40
    :...
    0.39
    ኃ
    0.39
    :**
    0.39
    :”
    0.39
    Ⴌ
    0.38
     چاہیے۔
    0.38
     vét
    0.37
    POSITIVE LOGITS
     among
    0.58
     face
    0.57
     Among
    0.52
    Among
    0.52
     Lay
    0.51
     lay
    0.50
     funcionan
    0.50
     Play
    0.50
    Lay
    0.50
     under
    0.50
    Activations Density 0.001%

    No Known Activations