INDEX

Explanations

descriptions of fastening devices that wrap around things

oai_token-act-pair · gemini-2.0-flash

wrapping and going around

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

 Roskov

-0.83

DockStyle

-0.74

 Paglinawan

-0.66

SequentialGroup

-0.62

 ménages

-0.61

contentLoaded

-0.59

المشاركات

-0.58

SourceChecksum

-0.58

WriteBarrier

-0.56

Personendaten

-0.56

POSITIVE LOGITS

 over

0.94

 around

0.81

over

0.74

Over

0.72

rededor

0.69

 OVER

0.69

Around

0.67

OVER

0.65

 Over

0.65

 Around

0.65

Activations Density 1.311%

descriptions of fastening devices that wrap around things

wrapping and going around

No Comments

No Known Activations