INDEX

Explanations

coordinating conjunctions in sentences that contain multiple ideas.

oai_token-act-pair · gemini-2.0-flash

and

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 فريبيس

-0.81

CompilerServices

-0.77

complexContent

-0.66

DockStyle

-0.65

 AssemblyProduct

-0.61

 esternos

-0.60

ليز

-0.59

webElementXpaths

-0.59

 Meksiku

-0.59

copg

-0.59

POSITIVE LOGITS

__*/

0.57

indicated

0.49

 indicates

0.47

indicates

0.46

catus

0.46

 indica

0.45

indication

0.45

 Hildebrand

0.44

 termica

0.44

 Away

0.43

Activations Density 2.601%

coordinating conjunctions in sentences that contain multiple ideas.

and

No Comments

No Known Activations