© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8799
    Prev
    Next
    INDEX
    Explanations

    Glassdoor.com

    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
     поги
    2.52
    j
    2.48
    ৩৯
    2.45
    ৩৭
    2.38
    ৪৮
    2.36
    ২৮
    2.34
    z
    2.27
    ৩৪
    2.24
    ৩৮
    2.22
    iendo
    2.21
    POSITIVE LOGITS
     lighthouse
    2.55
     leva
    2.52
    ра
    2.51
    boldsymbol
    2.45
     mouthful
    2.38
    rally
    2.36
     benevolent
    2.35
     viscous
    2.30
     forceful
    2.27
     juicy
    2.23
    Activations Density 0.000%

    No Known Activations