© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 218141
    Prev
    Next
    INDEX
    Explanations

    good intentions

    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_31_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
     inward
    0.38
    ᖏ
    0.37
     breezes
    0.35
     সাল
    0.34
    なら
    0.34
     Inlet
    0.34
    嬲
    0.33
    규모
    0.33
    aroos
    0.33
    ুষ
    0.32
    POSITIVE LOGITS
     intentions
    0.68
     intention
    0.66
     intended
    0.63
     intención
    0.59
     intending
    0.59
    intended
    0.57
     intends
    0.56
     намере
    0.55
     intend
    0.52
    intention
    0.52
    Activations Density 0.072%

    No Known Activations