© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 68097
    Prev
    Next
    INDEX
    Explanations

    distress

    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_46_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
     demand
    0.50
    纓
    0.44
     Demand
    0.41
     demands
    0.40
    xcs
    0.40
     certainly
    0.39
    demand
    0.39
    Demand
    0.39
     care
    0.38
    фере
    0.38
    POSITIVE LOGITS
    awi
    0.38
    Availability
    0.37
    iner
    0.37
    ઠ
    0.37
    ılım
    0.36
    ivia
    0.36
     Brow
    0.36
    onChange
    0.36
    ্যাপ
    0.35
    ერს
    0.35
    Activations Density 0.005%

    No Known Activations