© 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. 7861
    Prev
    Next
    INDEX
    Explanations

    instances of the words "this", "these", "clearly", or "more".

    oai_token-act-pair · gemini-2.0-flash

    clearly

    np_max-act · gemini-2.0-flash

    clearly

    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
     the
    -1.14
     this
    -1.12
     our
    -0.98
    AnchorStyles
    -0.90
     it
    -0.85
    __":
    -0.83
     therefore
    -0.82
    setVerticalGroup
    -0.81
    \{\\
    -0.80
    ScopeManager
    -0.79
    POSITIVE LOGITS
    '
    0.75
    dbach
    0.58
     Yoruba
    0.56
     canst
    0.56
     Maori
    0.55
     Poincar
    0.55
     divent
    0.54
     SUDOC
    0.54
    ('
    0.53
     Aurang
    0.53
    Activations Density 1.263%

    No Known Activations