© 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. 78215
    Prev
    Next
    INDEX
    Explanations

    consolation, solace, comfort

    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
     Fixing
    0.38
     Bxg
    0.38
     )-
    0.37
     controlled
    0.36
     Screw
    0.35
     tongs
    0.35
     Controlled
    0.35
     कॉम्प
    0.34
    ਪਣ
    0.34
     fixing
    0.34
    POSITIVE LOGITS
     consolation
    0.90
     solace
    0.78
     consola
    0.64
    安慰
    0.64
     comforted
    0.63
     conso
    0.61
    慰
    0.55
    consol
    0.51
     consol
    0.51
     امید
    0.50
    Activations Density 0.001%

    No Known Activations