© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 45807
    Prev
    Next
    INDEX
    Explanations

    transaction management

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_22_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
     prospecting
    0.40
    asos
    0.40
    ᒋ
    0.40
     creativity
    0.39
    مت
    0.39
    السلام
    0.38
    મે
    0.37
    દી
    0.37
     sneezing
    0.37
    زا
    0.37
    POSITIVE LOGITS
    ^{\
    0.46
    chodzi
    0.42
     nedost
    0.42
     അധ
    0.42
    visor
    0.41
    fter
    0.40
     feels
    0.40
     škole
    0.39
     Goes
    0.39
     exists
    0.38
    Activations Density 0.004%

    No Known Activations