INDEX

Explanations

the word "cutting" and its related variations

oai_token-act-pair · gemini-2.0-flash

cutting

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

Geplaatst

-0.69

ViewImports

-0.63

 HasFactory

-0.63

Ehrungen

-0.62

 odkazy

-0.61

<bos>

-0.60

)».

-0.60

 Cytometry

-0.60

+#+#

-0.60

 LatLng

-0.59

POSITIVE LOGITS

NameInMap

0.63

 typically

0.60

ájá

0.55

 Besch

0.55

versus

0.54

ことはありません

0.54

 Typically

0.54

 daily

0.54

 creș

0.54

LookAnd

0.53

Activations Density 5.234%

the word "cutting" and its related variations

cutting

No Comments

No Known Activations