© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 5712
    Prev
    Next
    INDEX
    Explanations

    states of being

    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_44_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
    峈
    0.37
     utilizamos
    0.37
    ණ්
    0.36
     enterr
    0.36
    వాన్ని
    0.36
     io
    0.36
    ístico
    0.35
    ائيه
    0.35
    닌
    0.35
     Rn
    0.35
    POSITIVE LOGITS
     yielding
    0.44
     having
    0.42
     experiencing
    0.41
     owning
    0.40
     disintegration
    0.38
     realizing
    0.38
    ()<<"
    0.37
     achieving
    0.37
    哺
    0.36
     knowing
    0.36
    Activations Density 0.454%

    No Known Activations