© 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. 2910
    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
    నా
    2.44
    an
    2.43
    인
    2.41
     USO
    2.41
     fant
    2.40
     சேர்த்து
    2.38
     interf
    2.31
    یه
    2.27
    ಕು
    2.22
    Tiene
    2.22
    POSITIVE LOGITS
    ি
    3.04
     keyboards
    3.03
    BTW
    2.72
     famed
    2.57
    ी
    2.56
     capitalizing
    2.55
    atives
    2.53
     ক্ষমতাসীন
    2.51
    ㇂
    2.48
    ariance
    2.45
    Activations Density 0.051%

    No Known Activations