© 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. 14761
    Prev
    Next
    INDEX
    Explanations

    locations or company names and scientific terms

    oai_token-act-pair · gemini-2.0-flash

    Academic references

    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
    AccessorTable
    -0.64
    ⓧ
    -0.64
     utafitiHapana
    -0.63
    }))
    -0.62
    oa̍t
    -0.57
     виправивши
    -0.57
    :+:
    -0.56
    )))
    -0.56
     désolés
    -0.56
    󠁿
    -0.56
    POSITIVE LOGITS
     quæ
    0.62
     Lambeth
    0.51
     ſtate
    0.50
     Mémoires
    0.48
     Prefeitura
    0.48
     Bucure
    0.44
     Moscou
    0.44
     Abidjan
    0.43
     Aachen
    0.43
    BagConstraints
    0.40
    Activations Density 3.241%

    No Known Activations