© 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. 3130
    Prev
    Next
    INDEX
    Explanations

    discourse markers

    oai_token-act-pair · gemini-2.0-flash

    might be

    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
     appear
    -2.11
     appeared
    -2.11
     appearing
    -2.08
     appearance
    -2.03
     Appearance
    -1.98
    appear
    -1.95
     Appears
    -1.94
    appearance
    -1.92
     appears
    -1.91
     apparent
    -1.84
    POSITIVE LOGITS
    #+#
    0.73
    UnusedPrivate
    0.72
     الرياضيه
    0.72
    ("")]
    0.64
    VIAF
    0.60
     dAtA
    0.59
    WriteBarrier
    0.58
    providedIn
    0.57
    migrationBuilder
    0.56
     requestCode
    0.56
    Activations Density 4.196%

    No Known Activations