© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3469
    Prev
    Next
    INDEX
    Explanations

    placeholder address

    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
    𝒐
    1.21
    uksen
    1.19
     hukum
    1.14
    ﮯ
    1.14
    ный
    1.14
    Женско
    1.13
     پسند
    1.12
    hadoop
    1.11
     ανέ
    1.09
     egen
    1.08
    POSITIVE LOGITS
    ι
    1.35
     outskirts
    1.32
     diethyl
    1.25
    ksi
    1.24
     resid
    1.24
     paar
    1.19
     accret
    1.19
     Payable
    1.18
     ears
    1.16
    #(
    1.16
    Activations Density 0.015%

    No Known Activations