© 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. 6680
    Prev
    Next
    INDEX
    Explanations

    locations and organizations, especially medical facilities, government institutions, and companies (often with abbreviations like MD, CA, MA and their full forms)

    oai_token-act-pair · gemini-2.0-flash

    references and addresses

    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
    )]
    -0.35
    "]),
    -0.33
    "=>$
    -0.31
    >")
    -0.31
    ”]
    -0.31
    "]];
    -0.31
    }}}
    -0.31
    }")]
    -0.31
    ")]
    -0.30
    ")),
    -0.30
    POSITIVE LOGITS
     habet
    0.83
     Grecs
    0.82
     tiegħek
    0.78
     itſelf
    0.78
     iſt
    0.77
     reaſon
    0.77
     quæ
    0.76
     myſelf
    0.75
     auffi
    0.73
     vnnd
    0.72
    Activations Density 31.733%

    No Known Activations