© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 7807
    Prev
    Next
    INDEX
    Explanations

    hexadecimal strings or other strings starting with '0's

    oai_token-act-pair · gemini-2.0-flash

    zero

    np_max-act · gemini-2.0-flash

    0 Method used: 1 — reason: all max activating tokens are 0 — explanation: 0

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    -2.89
    1
    -2.41
    2
    -2.38
    3
    -2.22
    4
    -2.13
    5
    -2.11
    6
    -2.05
    8
    -2.03
    7
    -1.98
    9
    -1.98
    POSITIVE LOGITS
    ^(@)
    2.39
     Efq
    2.25
     $_"
    2.13
    .}~\
    2.03
    %\]
    1.99
    )";
    1.99
    ſelf
    1.98
    )");
    1.97
    BibitemShut
    1.96
    — 
    1.95
    Activations Density 2.756%

    No Known Activations