INDEX

Explanations

words related to legal and medical contexts, also mathematical and statistical texts

oai_token-act-pair · gemini-2.0-flash

words related to legal documents and academic papers

np_token-act-pair-logits · gemini-2.0-flash

technical/legal documents

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

tituted

-0.66

ressee

-0.57

__);

-0.56

EMIA

-0.55

rungsseite

-0.54

}();

-0.54

getSingle

-0.53

ctif

-0.53

ITUTION

-0.52

zonych

-0.52

POSITIVE LOGITS

RenderAtEndOf

0.99

 typelib

0.82

 betweenstory

0.76

 springfox

0.68

 Meksiku

0.66

 '\\;'

0.66

CodedInputStream

0.63

цездатний

0.62

يكب

0.61

XmlAccessType

0.60

Activations Density 62.716%

words related to legal and medical contexts, also mathematical and statistical texts

words related to legal documents and academic papers

technical/legal documents

No Comments

No Known Activations