© 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. 251714
    Prev
    Next
    INDEX
    Explanations

    actions and change

    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
    
    0.40
     Grac
    0.37
    וּ
    0.37
     mein
    0.37
     _
    0.35
     Petsc
    0.35
    ѐ
    0.35
     როგორც
    0.35
     Lakeside
    0.34
     Ê
    0.34
    POSITIVE LOGITS
     nourished
    0.41
    Bring
    0.39
     emphasise
    0.39
    FOCUS
    0.38
     criticise
    0.38
    enhance
    0.38
     incorporation
    0.37
    ใส่
    0.37
     exaggerate
    0.37
     குறைக்க
    0.37
    Activations Density 0.018%

    No Known Activations