INDEX

Explanations

text containing advice or guidance from a professional

oai_token-act-pair · gemini-2.0-flash

a / an

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

PhysRevD

-0.89

 kasarigan

-0.76

bootstrapcdn

-0.69

findpost

-0.66

ValueStyle

-0.66

 <>",

-0.64

]--;

-0.63

يكب

-0.62

 oprot

-0.62

angsaan

-0.62

POSITIVE LOGITS

0.90

an

0.74

 seorang

0.63

 independent

0.59

 qualified

0.57

 unui

0.51

 competent

0.51

 experienced

0.49

 một

0.48

一名

0.48

Activations Density 1.515%

text containing advice or guidance from a professional

a / an

No Comments

No Known Activations