© 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
    2. Gemma-3-27B-IT
    3. 38-GEMMASCOPE-2-TRANSCODER-262K
    4. 465
    Prev
    Next
    INDEX
    Explanations

    code interpolation with variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_38_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
     Jean
    0.41
     wonder
    0.38
    <!--
    0.38
     Howard
    0.38
     Michelle
    0.37
    hees
    0.37
    lees
    0.37
     <!--
    0.36
    expl
    0.36
    рядок
    0.36
    POSITIVE LOGITS
     ذمہ
    0.36
    }')
    0.35
    াচার
    0.35
    রিষ্ঠ
    0.35
    }^{+}=
    0.34
    格
    0.33
     объ
    0.32
     მო
    0.32
     정의
    0.32
    ॰ऍ
    0.32
    Activations Density 0.059%

    No Known Activations