© 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. 7971
    Prev
    Next
    INDEX
    Explanations

    achieve, reach, destination, goals

    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
    на
    2.85
    സ്ലാ
    2.64
     سازی
    2.61
    𝑖
    2.59
    𝐀
    2.55
    ल
    2.55
    en
    2.48
    MIUM
    2.46
    ık
    2.46
    𝑑
    2.46
    POSITIVE LOGITS
    ेल
    2.75
    ش
    2.73
    ુ
    2.58
    un
    2.49
     antaranya
    2.41
    র
    2.32
    upper
    2.26
     queda
    2.26
    انک
    2.26
    ού
    2.22
    Activations Density 0.059%

    No Known Activations