© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 327
    Prev
    Next
    INDEX
    Explanations

    phrases indicating importance or necessity

    oai_token-act-pair · gemini-2.0-flash

    reasons or explanations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    LookAnd
    -0.56
     armis
    -0.54
     للمعارف
    -0.52
    VersionUID
    -0.51
    ритори
    -0.50
    SPATH
    -0.50
     springfox
    -0.48
     Mith
    -0.47
    NameInMap
    -0.46
    fuse
    -0.45
    POSITIVE LOGITS
    iettivo
    0.68
    govine
    0.59
    virons
    0.56
    AccessFile
    0.55
    期刊论文
    0.54
    VolleyError
    0.53
    strando
    0.52
    Portale
    0.52
    MessageType
    0.50
    shutil
    0.50
    Activations Density 1.476%

    No Known Activations