© 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. 9329
    Prev
    Next
    INDEX
    Explanations

    a variety of function words like prepositions articles conjunctions often preceding nouns

    oai_token-act-pair · gemini-2.0-flash

    routes and paths

    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
     Lines
    -1.23
     LINES
    -1.13
     routes
    -1.13
     Paths
    -1.09
     Roads
    -1.08
    Lines
    -1.07
     Routes
    -1.07
     lines
    -1.06
    routes
    -1.05
     paths
    -1.05
    POSITIVE LOGITS
    Autoritní
    0.66
     estekak
    0.65
    发表于
    0.60
    NUMX
    0.59
    المناصب
    0.58
    apunov
    0.54
    verifyException
    0.54
    ModelSerializer
    0.53
     myſelf
    0.51
    ViewChild
    0.50
    Activations Density 5.844%

    No Known Activations