INDEX

Explanations

words expressing beliefs or convictions

oai_token-act-pair · gemini-2.0-flash

that believe

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

追

-0.47

 otherwise

-0.45

向

-0.44

marily

-0.44

 further

-0.42

 upcoming

-0.42

 candidate

-0.42

↵

-0.42

Ecotoxicity

-0.42

trk

-0.41

POSITIVE LOGITS

IndentedString

0.87

 Roskov

0.77

Autoritní

0.75

HtmlAttribute

0.73

sidemargin

0.73

tagHelper

0.71

 AssemblyCulture

0.71

цездатний

0.70

 '\\;'

0.69

 autorytatywna

0.68

Activations Density 0.651%

words expressing beliefs or convictions

that believe

No Comments

No Known Activations