© 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. 8720
    Prev
    Next
    INDEX
    Explanations

    cubic, cubics

    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
    つまり
    3.16
    ت
    2.90
    า
    2.75
    thirds
    2.74
    і
    2.61
    리를
    2.59
    का
    2.57
    いて
    2.45
    리에
    2.43
    漢
    2.43
    POSITIVE LOGITS
     bxc
    2.53
    ﻲ
    2.52
    icle
    2.47
    mib
    2.43
    modifier
    2.42
    nasium
    2.42
    ᡠ
    2.41
     सौदा
    2.39
     modulus
    2.36
    _{[
    2.35
    Activations Density 0.026%

    No Known Activations