© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 211178
    Prev
    Next
    INDEX
    Explanations

    aproximadamente / aproximación

    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_5_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
    ور
    1.58
    re
    1.26
    。
    1.22
    1.16
    》。
    1.16
    ре
    1.13
    な
    1.13
    ור
    1.10
    )،
    1.09
    فت
    1.08
    POSITIVE LOGITS
    t
    2.27
    ა
    1.64
    ,
    1.52
    т
    1.32
    ت
    1.27
     t
    1.23
     l
    1.18
    er
    1.16
    AR
    1.16
    IT
    1.16
    Activations Density 0.016%

    No Known Activations