© 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. 7630
    Prev
    Next
    INDEX
    Explanations

    ReactDOM from

    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
    ο
    2.59
    у
    2.51
    ר
    2.46
    ッグ
    2.40
     nedenle
    2.21
    শ
    2.16
    er
    2.15
    されている
    2.14
    עת
    2.13
     sayıda
    2.13
    POSITIVE LOGITS
    स्परिक
    2.77
     hindrance
    2.70
    忑
    2.62
    รับ
    2.51
    𝘁
    2.39
    ButtonPressed
    2.38
    𝗻
    2.37
     rectifier
    2.34
    raviolet
    2.33
     mixt
    2.32
    Activations Density 0.000%

    No Known Activations