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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9901
    Prev
    Next
    INDEX
    Explanations

    verbs or adjectives relating actions or states of being

    oai_token-act-pair · gemini-2.0-flash

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     cross
    -1.88
    cross
    -1.67
     Cross
    -1.64
    Cross
    -1.59
     CROSS
    -1.41
    CROSS
    -1.35
     cros
    -1.05
     crosses
    -1.04
    cros
    -0.86
    クロス
    -0.79
    POSITIVE LOGITS
    ########.
    0.52
    mylist
    0.47
    acterium
    0.46
    oznam
    0.46
    mapreduce
    0.46
    BufferException
    0.43
     numerus
    0.43
    GetKey
    0.42
     sign
    0.42
    änomen
    0.40
    Activations Density 5.537%

    No Known Activations