© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 16180
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to plans for the future, advice, or expectations

    oai_token-act-pair · gemini-2.0-flash

    planning to do something

    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
     varandra
    -1.28
     auroit
    -1.19
     avoient
    -1.16
     normaux
    -1.13
     étoit
    -1.13
     pouvoit
    -1.12
     feroit
    -1.11
     quelcon
    -1.11
     étoient
    -1.10
     définiti
    -1.09
    POSITIVE LOGITS
     get
    0.89
     create
    0.85
     write
    0.84
     discuss
    0.83
     apply
    0.83
     eat
    0.82
     define
    0.82
     find
    0.82
     to
    0.81
     compare
    0.81
    Activations Density 25.704%

    No Known Activations