© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8766
    Prev
    Next
    INDEX
    Explanations

    angle brackets and code like syntax snippets

    oai_token-act-pair · gemini-2.0-flash

    code syntax elements and API versioning

    np_token-act-pair-logits · gpt-4o-mini

    programming symbols

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    "]:
    -1.54
    ']:
    -1.52
    "):
    -1.45
    '):
    -1.44
    )]:
    -1.30
    ）。
    -1.29
    '):
    -1.28
    ']):
    -1.25
    」。
    -1.23
    "):
    -1.22
    POSITIVE LOGITS
    )
    0.84
    "
    0.65
    ”
    0.63
    ]
    0.60
    )"
    0.58
    ")
    0.56
    </i>
    0.56
    ()
    0.55
    ]"
    0.52
    }
    0.52
    Activations Density 15.212%

    No Known Activations