© 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. 8653
    Prev
    Next
    INDEX
    Explanations

    words that are commonly used when giving advice

    oai_token-act-pair · gemini-2.0-flash

    what

    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
     as
    -0.65
     within
    -0.52
     with
    -0.51
     Are
    -0.46
     cuantos
    -0.43
     be
    -0.42
     through
    -0.42
     Make
    -0.41
     Abstract
    -0.40
     Use
    -0.40
    POSITIVE LOGITS
     itſelf
    1.00
     Jefus
    0.97
     purpoſe
    0.95
     pleaſure
    0.95
     houſe
    0.94
     Monfieur
    0.86
     Majefty
    0.84
    цездатний
    0.83
     ſever
    0.83
     myſelf
    0.82
    Activations Density 13.050%

    No Known Activations