© 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. 8784
    Prev
    Next
    INDEX
    Explanations

    what looks like a garbled advertisement from a college newspaper

    oai_token-act-pair · gemini-2.0-flash

    Document snippets

    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
     utafitiHapana
    -0.78
    Personensuche
    -0.77
    InjectAttribute
    -0.75
    rungsseite
    -0.71
    MemoryWarning
    -0.69
     beginnetje
    -0.68
     estekak
    -0.67
    seamnă
    -0.66
    ValueStyle
    -0.63
     giudi
    -0.63
    POSITIVE LOGITS
    ALU
    0.49
    ruary
    0.49
    encils
    0.49
    unicip
    0.49
    elfare
    0.48
    ousands
    0.47
    KAM
    0.47
    ldg
    0.46
     SI
    0.46
    UNT
    0.46
    Activations Density 4.183%

    No Known Activations