© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 8908
    Prev
    Next
    INDEX
    Explanations

    words or fragments of words ending in "ic" or "ally" or related to electronics or electricity

    oai_token-act-pair · gemini-2.0-flash

    ally

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    IntoConstraints
    -0.65
    GEBURTSDATUM
    -0.60
    ("")]
    -0.56
    mobileqq
    -0.54
     Roskov
    -0.49
     mappa
    -0.49
    AndroidJUnit
    -0.46
     verliert
    -0.46
    PreferredItem
    -0.45
    mMap
    -0.44
    POSITIVE LOGITS
     elec
    0.98
     Elec
    0.96
     Elect
    0.93
     elect
    0.86
     ELECT
    0.84
    Elec
    0.83
     ELE
    0.83
    Elect
    0.82
     electric
    0.82
     Electro
    0.81
    Activations Density 0.266%

    No Known Activations