© 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. 14880
    Prev
    Next
    INDEX
    Explanations

    Java code with database insertions, exception messages, and statistics

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    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
    SourceChecksum
    -0.91
     nakalista
    -0.91
    ."]
    -0.88
    ,‎
    -0.83
    .";
    -0.81
    ."));
    -0.81
    InjectAttribute
    -0.80
    PhysRev
    -0.79
    .',
    -0.78
    ,»
    -0.77
    POSITIVE LOGITS
     ochi
    0.52
    ΙΝ
    0.50
     wyp
    0.50
    έλ
    0.48
     εγ
    0.47
    temp
    0.47
    mon
    0.46
     κοιν
    0.46
     dimo
    0.45
     zmien
    0.44
    Activations Density 4.471%

    No Known Activations