© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 6558
    Prev
    Next
    INDEX
    Explanations

    after a + duration/event

    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
    (\
    1.46
    ১
    1.29
    igion
    1.18
    (\{
    1.14
    -\
    1.11
    rowser
    1.09
    儡
    1.09
     Underlying
    1.06
    ع
    1.04
    rité
    1.03
    POSITIVE LOGITS
    на
    1.23
    स
    1.19
    湎
    1.17
    dicke
    1.16
    ен
    1.14
    cantidad
    1.13
     typo
    1.10
    কোনও
    1.10
     compartmental
    1.10
    Straw
    1.10
    Activations Density 0.078%

    No Known Activations