© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 148595
    Prev
    Next
    INDEX
    Explanations

    ix

    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_59_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
    ឡិចត្រូ
    0.39
     piss
    0.37
    ช่อง
    0.37
    য্
    0.37
     接
    0.35
    ड़ा
    0.35
     நீர்
    0.35
    বাদে
    0.35
    ϓ
    0.34
    hitth
    0.34
    POSITIVE LOGITS
    ix
    2.66
    IX
    2.66
     ix
    2.66
     IX
    2.63
     Ix
    2.08
    Ix
    1.83
    ixes
    1.77
    ixe
    1.65
    ixa
    1.58
     VIII
    1.57
    Activations Density 0.033%

    No Known Activations