© 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
    2. Gemma-3-4B-IT
    3. 3-GEMMASCOPE-2-TRANSCODER-262K
    4. 8518
    Prev
    Next
    INDEX
    Explanations

    Bayesian statistics and methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_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
    ا
    3.16
    ف
    3.02
    ]}$
    2.54
    ுக
    2.29
    ]$
    2.27
    }$\\
    2.19
    otf
    2.14
     चलकर
    2.10
    леп
    2.07
    ா
    2.04
    POSITIVE LOGITS
     kuri
    2.29
    rische
    2.28
    रात्रि
    2.27
    n
    2.25
     საშუალ
    2.24
     demanding
    2.24
    眙
    2.20
     wiper
    2.20
    dou
    2.19
     приме
    2.16
    Activations Density 0.023%

    No Known Activations