© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 104082
    Prev
    Next
    INDEX
    Explanations

    soft

    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_44_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
     hard
    0.91
    hard
    0.86
     HARD
    0.82
    Hard
    0.80
     Hard
    0.80
    硬
    0.77
     हार्ड
    0.74
     hardest
    0.68
    HARD
    0.66
     hår
    0.64
    POSITIVE LOGITS
     soft
    2.48
     Soft
    2.28
    Soft
    2.25
    soft
    2.22
     SOFT
    2.03
    软
    2.00
     सॉफ्ट
    1.97
     мяг
    1.92
     softness
    1.91
    ソフト
    1.91
    Activations Density 0.142%

    No Known Activations