© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5122
    Prev
    Next
    INDEX
    Explanations

    localStorage.getItem or AsyncStorage.getItem

    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
     penetrate
    1.27
    اته
    1.21
    }=
    1.17
     rng
    1.16
    стью
    1.15
    িং
    1.15
    perturbative
    1.09
     contemplated
    1.07
    {(
    1.07
    ery
    1.05
    POSITIVE LOGITS
    ר
    1.16
    rangian
    1.07
    ங்கிணை
    1.06
     ชม
    1.04
     cont
    1.04
    ра
    1.04
     aback
    1.03
    ?,?,
    1.02
     fool
    1.02
     بسي
    1.01
    Activations Density 0.001%

    No Known Activations