© 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. 3387
    Prev
    Next
    INDEX
    Explanations

    a variety of words with little apparent connection to each other, but with a slight preference for plot points and medical terms

    oai_token-act-pair · 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
     chapels
    -0.71
     acids
    -0.71
     trenches
    -0.69
    hibitions
    -0.69
    wells
    -0.68
     altars
    -0.68
    ologies
    -0.68
     carbons
    -0.68
    vities
    -0.68
    Sets
    -0.67
    POSITIVE LOGITS
    ViewFeatures
    0.47
     autorytatywna
    0.42
    providedIn
    0.40
     estekak
    0.40
     EconPapers
    0.35
    bone
    0.33
     المعيارى
    0.33
    tvguidetime
    0.31
    bay
    0.30
     forState
    0.30
    Activations Density 9.072%

    No Known Activations