© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 253135
    Prev
    Next
    INDEX
    Explanations

    Balcony

    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
    懒
    0.39
     माह
    0.38
     přek
    0.38
     Fors
    0.37
    ాలా
    0.37
    Pada
    0.37
    ający
    0.37
    aving
    0.36
    机票
    0.36
    izing
    0.36
    POSITIVE LOGITS
    l
    0.40
    stö
    0.40
     टेल
    0.39
    тни
    0.36
    lini
    0.36
     पुनर्
    0.35
     Linz
    0.35
     hàn
    0.35
    leiter
    0.35
    线性
    0.34
    Activations Density 0.000%

    No Known Activations