© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9130
    Prev
    Next
    INDEX
    Explanations

    code snippets or mathematical expressions with punctuation and hyphenated words

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    ting
    -1.09
    ding
    -1.03
    ning
    -1.03
     ringing
    -1.02
    TING
    -1.02
    ring
    -1.00
    DING
    -0.98
    GING
    -0.98
    ing
    -0.95
    ging
    -0.95
    POSITIVE LOGITS
    <bos>
    0.48
     dima
    0.47
    פר
    0.46
     navigate
    0.44
    practi
    0.43
     manage
    0.43
    embatan
    0.43
    employed
    0.43
    idavit
    0.42
    phosphat
    0.42
    Activations Density 2.248%

    No Known Activations