© 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-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 3868
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_2_width_16k_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
    و
    3.10
    an
    3.03
     semblance
    2.80
    and
    2.77
    אנ
    2.65
    om
    2.62
    ings
    2.61
    breaking
    2.55
    ান
    2.51
    ता
    2.41
    POSITIVE LOGITS
    পন্থী
    2.71
    ют
    2.65
    """"
    2.56
    LastGenOutput
    2.52
    蛄
    2.43
     potrivit
    2.41
    }=
    2.41
    ться
    2.39
     bois
    2.39
     sprouts
    2.37
    Activations Density 0.030%

    No Known Activations