© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10300
    Prev
    Next
    INDEX
    Explanations

    mathematical notations, equations, tables, and references

    oai_token-act-pair · gemini-2.0-flash

    mathematical/code related

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     \%$
    -0.91
     متعلقه
    -0.91
    }$)
    -0.90
    })$
    -0.90
    ]$
    -0.89
    }$
    -0.89
    |$
    -0.87
    ))$
    -0.85
     ?$
    -0.84
     *}$
    -0.83
    POSITIVE LOGITS
     .
    0.44
    mtable
    0.40
     po
    0.38
    ).
    0.38
     •
    0.37
    )
    0.37
    Kit
    0.36
     blod
    0.36
     ra
    0.35
    alité
    0.35
    Activations Density 13.845%

    No Known Activations