© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3165
    Prev
    Next
    INDEX
    Explanations

    `f`, `0.0`, `1.0`, `4.0`, `2.0`

    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_5_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
     comboBox
    0.82
    ⺆
    0.82
    𝗽
    0.79
     sortes
    0.78
    𝗱
    0.77
    𝘁
    0.72
    𝗹
    0.72
     erit
    0.72
     pretende
    0.71
    𝘆
    0.71
    POSITIVE LOGITS
    <bos>
    0.76
    સર
    0.67
     nowhere
    0.65
     fault
    0.64
    unity
    0.62
     लिखी
    0.61
     supposed
    0.60
    Qatar
    0.59
    man
    0.59
     blame
    0.59
    Activations Density 0.015%

    No Known Activations