© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 180736
    Prev
    Next
    INDEX
    Explanations

    tower of hanoi puzzle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_24_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
    。",
    0.42
    encode
    0.42
     চন্দ্র
    0.42
    があり
    0.40
    trusted
    0.39
    establish
    0.38
    খ্যান
    0.38
    丏
    0.38
    addClass
    0.37
     obil
    0.37
    POSITIVE LOGITS
     Baroque
    0.42
    ませんでした
    0.40
     Bib
    0.40
     op
    0.38
    ková
    0.38
     clauses
    0.38
     Bibliography
    0.38
     Clauses
    0.38
     Call
    0.37
    ൦
    0.37
    Activations Density 0.001%

    No Known Activations