© 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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 11971
    Prev
    Next
    INDEX
    Explanations

    passages about social mobility or progress, often using the metaphor of climbing or a ladder.

    oai_token-act-pair · gemini-2.0-flash

    Climbing and ascent

    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
     climbing
    -2.09
     climb
    -1.98
     Climbing
    -1.91
     Climb
    -1.90
    Climbing
    -1.88
     climber
    -1.83
     climbed
    -1.81
    climbing
    -1.77
     climbs
    -1.77
    climb
    -1.77
    POSITIVE LOGITS
    llus
    0.58
    setVerticalGroup
    0.57
    IsMutable
    0.56
    LabelTagHelper
    0.50
    лот
    0.49
    SpringBootTest
    0.48
     initWithFrame
    0.46
    InteropServices
    0.46
    XMLSchema
    0.45
     Diretto
    0.45
    Activations Density 1.312%

    No Known Activations