© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8513
    Prev
    Next
    INDEX
    Explanations

    references to basketball, and especially to the NBA

    oai_token-act-pair · gemini-2.0-flash

    Basketball player discussions

    np_max-act-logits · gemini-2.0-flash

    say "capitalized names"

    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_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
     الحره
    -0.57
    Бахар
    -0.56
     newBuilder
    -0.56
     جات
    -0.56
    }")]
    -0.54
    mtrl
    -0.54
    lccn
    -0.54
     gynhyrchwyd
    -0.52
    stdc
    -0.52
     Wage
    -0.51
    POSITIVE LOGITS
    évaluateur
    0.66
    lapsingToolbar
    0.65
    TagMode
    0.59
    adaptiveStyles
    0.56
    cplusplus
    0.52
    +#+#
    0.50
    JvmStatic
    0.50
    ēju
    0.48
     splashes
    0.46
    minecraftforge
    0.46
    Activations Density 4.273%

    No Known Activations