© 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. 202497
    Prev
    Next
    INDEX
    Explanations

    cold

    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
    呼
    0.38
    áž
    0.38
    colFirst
    0.38
     विधि
    0.37
     দাগ
    0.36
    вок
    0.36
     Wsp
    0.35
     PK
    0.35
    Pk
    0.35
    EY
    0.35
    POSITIVE LOGITS
     cold
    0.54
    Cold
    0.47
    เย็น
    0.47
    冷
    0.46
     Cold
    0.45
    cold
    0.43
    冷的
    0.42
     frío
    0.42
     холод
    0.41
     ঠান্ডা
    0.41
    Activations Density 0.001%

    No Known Activations