© 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
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 10600
    Prev
    Next
    INDEX
    Explanations

    verbs in passive voice or past tense

    oai_token-act-pair · gemini-2.0-flash

    Relay information

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     seen
    -0.82
     Seen
    -0.76
    seen
    -0.74
    Seen
    -0.74
     SEEN
    -0.68
     visto
    -0.65
     spotted
    -0.64
     observed
    -0.59
     accused
    -0.58
     heard
    -0.56
    POSITIVE LOGITS
     تانيه
    0.74
    MigrationBuilder
    0.73
    AsUp
    0.72
     informed
    0.63
    GraphicsUnit
    0.59
     jLabel
    0.58
     للمعارف
    0.54
    informed
    0.54
    тисти
    0.54
     فريبيس
    0.53
    Activations Density 1.588%

    No Known Activations