© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 21887
    Prev
    Next
    INDEX
    Explanations

    slave

    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
     Slavery
    0.59
     slavery
    0.59
     jScrollPane
    0.40
     Meng
    0.39
    oyl
    0.38
    }}}
    0.37
    lavery
    0.36
     TextInput
    0.36
    ܣ
    0.36
    垒
    0.35
    POSITIVE LOGITS
     fugitive
    0.59
     free
    0.59
    Nat
    0.58
     Denmark
    0.58
    Frederick
    0.58
     Nat
    0.57
     runaway
    0.57
     masters
    0.56
     ens
    0.55
     Fug
    0.55
    Activations Density 0.047%

    No Known Activations