© 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. 717
    Prev
    Next
    INDEX
    Explanations

    dialogue attributed to different characters, especially men and women

    oai_token-act-pair · gemini-2.0-flash

    Narratives and dialogues

    np_max-act-logits · gemini-2.0-flash
    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
     الحره
    -0.56
     promocional
    -0.54
    MemoryWarning
    -0.52
     Meksiku
    -0.51
    گاری
    -0.49
     taker
    -0.48
     صوتيه
    -0.47
     HX
    -0.47
     Dura
    -0.46
    AntiForgeryToken
    -0.44
    POSITIVE LOGITS
    XtraEditors
    0.65
    DotNetBar
    0.61
    حوالہ
    0.58
    MS
    0.55
    CppMethod
    0.54
     nahilalakip
    0.53
    bibitem
    0.53
     utafitiHapana
    0.52
     betweenstory
    0.52
    hdys
    0.52
    Activations Density 2.378%

    No Known Activations