© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 12746
    Prev
    Next
    INDEX
    Explanations

    environmental degradation

    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_13_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
    கள்
    0.63
     למ
    0.51
    களை
    0.49
    ТИ
    0.49
    Y
    0.49
     GU
    0.47
     tablero
    0.47
    pInBuffer
    0.46
     magnific
    0.46
    Spain
    0.46
    POSITIVE LOGITS
     Chúa
    0.47
    ருக்கு
    0.46
    䄪
    0.45
    optera
    0.45
    jach
    0.45
    环保
    0.44
    粗
    0.44
    ozone
    0.43
    污染
    0.43
     опас
    0.42
    Activations Density 0.037%

    No Known Activations