© 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. 273
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs and other words acting as sentence connectors

    oai_token-act-pair · gemini-2.0-flash

    technical question/answer texts

    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
     يتيمه
    -0.66
    ніципа
    -0.65
    rrggbb
    -0.64
     gynhyrchwyd
    -0.60
    principalTable
    -0.58
    sizeCache
    -0.55
    styleType
    -0.55
     Vorles
    -0.55
    assertEqual
    -0.51
    raszamy
    -0.51
    POSITIVE LOGITS
    UnitTesting
    0.54
     Condu
    0.50
     onPostExecute
    0.49
    am
    0.47
     levier
    0.47
    ">//
    0.44
     Deta
    0.43
    RepeatedField
    0.43
     kasarigan
    0.42
    aah
    0.42
    Activations Density 8.450%

    No Known Activations