© 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. 15897
    Prev
    Next
    INDEX
    Explanations

    the phrase "hard to" and related words

    oai_token-act-pair · gemini-2.0-flash

    hard

    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
    XmlAccessType
    -0.68
    KommentareTeilen
    -0.67
     EconPapers
    -0.66
     tryck
    -0.65
    isContained
    -0.65
    Cyfeiriadau
    -0.64
     japonaise
    -0.61
     národ
    -0.61
    insics
    -0.60
    adaptiveStyles
    -0.60
    POSITIVE LOGITS
     most
    0.78
    most
    0.53
    Most
    0.51
    dAtA
    0.49
     nap
    0.49
     MOST
    0.47
    MOST
    0.45
     sharing
    0.44
     following
    0.44
     creating
    0.44
    Activations Density 7.913%

    No Known Activations