© 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-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8731
    Prev
    Next
    INDEX
    Explanations

    code snippets in various programming languages separated by natural language

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    np_max-act-logits · gemini-2.0-flash

    Portuguese

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    |}{}
    -0.57
     typelib
    -0.57
     виправивши
    -0.54
     Sélection
    -0.52
     nakalista
    -0.52
     Majefty
    -0.51
     CHAPITRE
    -0.50
    fjspx
    -0.50
     poffible
    -0.50
     purpoſe
    -0.50
    POSITIVE LOGITS
    מונות
    0.43
     døde
    0.43
    energies
    0.43
     spørsmål
    0.40
    LOYE
    0.38
    CHREIB
    0.38
    stellungs
    0.38
    oltre
    0.38
    observations
    0.36
    quela
    0.36
    Activations Density 1.819%

    No Known Activations