© 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. 3390
    Prev
    Next
    INDEX
    Explanations

    names with diacritics and the letter "z"

    oai_token-act-pair · gemini-2.0-flash

    z

    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
    ↵
    -0.44
     
    -0.43
    C
    -0.42
     dan
    -0.41
     N
    -0.40
     a
    -0.40
     R
    -0.38
     x
    -0.37
     C
    -0.37
    <eos>
    -0.36
    POSITIVE LOGITS
     Monfieur
    1.28
     myſelf
    1.23
     ſtate
    1.20
     ſeveral
    1.20
     ſever
    1.17
     Eſ
    1.17
     pleaſure
    1.16
     raiſ
    1.16
     Theſe
    1.15
     itſelf
    1.13
    Activations Density 0.267%

    No Known Activations