© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 14137
    Prev
    Next
    INDEX
    Explanations

    grammatical constructs with "allow", "that", "which", and "would" and also negation.

    oai_token-act-pair · gemini-2.0-flash

    Permissions and allowances

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     Allow
    -2.59
     allowed
    -2.59
     allow
    -2.52
    Allow
    -2.52
     allowing
    -2.47
     Allowing
    -2.47
    allow
    -2.39
     permit
    -2.33
     permitting
    -2.33
     allows
    -2.31
    POSITIVE LOGITS
    ]")]
    0.71
     &___
    0.59
    tagext
    0.58
     terecht
    0.55
    łbym
    0.55
    \{\\
    0.54
    śl
    0.54
     Stead
    0.52
    createQuery
    0.51
    fromnode
    0.51
    Activations Density 2.032%

    No Known Activations