© 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. 9192
    Prev
    Next
    INDEX
    Explanations

    the end of a quoted portion of text, marked by brackets

    oai_token-act-pair · gemini-2.0-flash

    words starting with "he"

    np_max-act-logits · 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
    AndEndTag
    -0.61
    how
    -0.52
    étape
    -0.50
    коном
    -0.47
    PostMapping
    -0.47
     how
    -0.46
    niad
    -0.45
     crossorigin
    -0.44
     }{@
    -0.44
     How
    -0.44
    POSITIVE LOGITS
    he
    0.91
    helial
    0.63
    heel
    0.63
    hé
    0.63
    helen
    0.62
    h
    0.62
    hall
    0.59
    hek
    0.59
    ra
    0.58
    hax
    0.57
    Activations Density 2.542%

    No Known Activations