© 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. 249111
    Prev
    Next
    INDEX
    Explanations

    meso-

    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
     Phoenix
    0.42
    FinishLaunching
    0.38
     phoenix
    0.38
     Phe
    0.38
     диф
    0.37
    ﮟ
    0.36
     equatorial
    0.36
     McGrath
    0.35
    ැ
    0.35
    NST
    0.35
    POSITIVE LOGITS
     mes
    1.75
     Mes
    1.38
    Mes
    1.28
    mes
    1.22
     sag
    1.06
     MES
    1.05
    MES
    0.90
     meso
    0.81
     Son
    0.80
     tumble
    0.80
    Activations Density 0.001%

    No Known Activations