© 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. 6947
    Prev
    Next
    INDEX
    Explanations

    narrowing down

    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
    ordre
    2.31
     PBMCs
    2.26
    භ
    2.26
     pomoć
    2.18
     sicurezza
    2.18
     Tư
    2.17
    asText
    2.13
    सर
    2.08
     mitigate
    2.07
    ᴇ
    2.06
    POSITIVE LOGITS
    ت
    2.63
    eine
    2.30
    en
    2.21
    +++
    2.17
    ein
    2.14
     trám
    2.05
    ത്
    2.05
    ooo
    1.98
     crystall
    1.97
     কিন্তু
    1.97
    Activations Density 0.019%

    No Known Activations