© 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. 5160
    Prev
    Next
    INDEX
    Explanations

    eating out

    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
    hit
    1.15
    handed
    1.15
    carga
    1.11
    peut
    1.06
    рда
    1.06
    tion
    1.05
    р
    1.05
    a
    1.03
    idee
    1.03
    Emb
    1.02
    POSITIVE LOGITS
    ına
    1.69
    et
    1.29
    тат
    1.27
     getIntent
    1.23
    и
    1.18
    בּ
    1.16
    此之外
    1.16
     bebidas
    1.15
    𝒄
    1.11
    RICAL
    1.11
    Activations Density 0.013%

    No Known Activations