© 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. 1104
    Prev
    Next
    INDEX
    Explanations

    names beginning with 'al-', location names and numbers

    oai_token-act-pair · gemini-2.0-flash

    Location and people names

    np_max-act-logits · gemini-2.0-flash

    al- Method used: 1 — because MAX_ACTIVATING_TOKENS are the same subword, so "al-"

    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
     resourceCulture
    -0.26
    sphase
    -0.25
    +)/
    -0.23
    ricated
    -0.21
    ämpfung
    -0.21
    ofition
    -0.21
    ）』
    -0.20
    Interface
    -0.20
     leaſt
    -0.20
    ？』
    -0.20
    POSITIVE LOGITS
    Angelina
    0.50
    Harvey
    0.49
     surla
    0.49
    Jeanne
    0.49
    +:+
    0.48
    Richie
    0.47
    Whitney
    0.47
    Samson
    0.47
    Saul
    0.47
    Rodney
    0.47
    Activations Density 40.552%

    No Known Activations