© 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. 8036
    Prev
    Next
    INDEX
    Explanations

    fall of

    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
     blower
    2.11
    iterranean
    2.07
     scoot
    2.05
    라
    2.01
     Keci
    2.01
    র্য
    2.00
    𝘮
    2.00
     cull
    2.00
    𝘷
    1.99
     jumper
    1.97
    POSITIVE LOGITS
     asleep
    2.13
    д
    2.09
    ʿ
    2.08
    ስ
    1.97
    enqueue
    1.89
    ोसी
    1.88
     asent
    1.85
     இதுவரை
    1.82
    carbons
    1.81
     agreg
    1.81
    Activations Density 0.049%

    No Known Activations