© 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. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 63
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_2_width_16k_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
    }$
    0.82
    +}$
    0.81
    }$.
    0.74
    }$;
    0.70
    可以说
    0.66
    ʟ
    0.66
    𝘺
    0.65
    }${
    0.64
     нет
    0.64
    где
    0.63
    POSITIVE LOGITS
    ല്ലാം
    0.81
    RA
    0.71
    ून
    0.71
    특별시
    0.68
     ampliamente
    0.68
    asmuch
    0.67
    िता
    0.63
    zwe
    0.63
     للغاية
    0.62
    यत
    0.61
    Activations Density 1.919%

    No Known Activations