© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 5067
    Prev
    Next
    INDEX
    Explanations

    html attributes and directives

    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
    e
    2.34
     sufferer
    2.11
    さて
    2.10
    ी
    2.08
     rift
    2.08
    ्स
    2.05
    इ
    2.03
    survival
    2.02
    ╰
    2.02
    劑
    2.02
    POSITIVE LOGITS
    л
    3.17
    u
    2.76
    ل
    2.52
    त
    2.42
    ፍተኛ
    2.37
    atge
    2.26
    ्य
    2.24
     scrollTo
    2.18
    ▥
    2.10
     CPE
    2.08
    Activations Density 0.007%

    No Known Activations