© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3953
    Prev
    Next
    INDEX
    Explanations

    negative statements about problems or difficulties

    oai_token-act-pair · gemini-2.0-flash

    a

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     fattori
    -0.54
    cipais
    -0.52
    Causas
    -0.52
    Causes
    -0.50
    ScopeManager
    -0.50
     définiti
    -0.50
     fatores
    -0.48
     causas
    -0.48
     ragioni
    -0.47
    dymyr
    -0.47
    POSITIVE LOGITS
    StoryboardSegue
    0.79
    UserScript
    0.75
    发表于
    0.69
    دانشنامهٔ
    0.68
     contextLoads
    0.66
     Autorisations
    0.64
    UnsafeEnabled
    0.63
    ErrUnexpectedEOF
    0.63
    下载附件
    0.60
     /\.(
    0.59
    Activations Density 4.398%

    No Known Activations