© 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. 7234
    Prev
    Next
    INDEX
    Explanations

    episode descriptions

    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
    𝑘
    1.23
    𝑙
    1.19
    𝑚
    1.15
    𝑛
    1.09
    ד
    1.06
    𝑝
    1.05
    Assim
    1.03
    もの
    1.03
    𝑡
    1.00
    ००
    0.99
    POSITIVE LOGITS
    ar
    1.43
     eyebrows
    1.23
     turbidity
    1.22
     насеко
    1.20
    𝗼
    1.19
     incr
    1.19
     excitations
    1.18
     easing
    1.14
     окре
    1.13
     inaction
    1.11
    Activations Density 0.003%

    No Known Activations