INDEX

Explanations

travel and tourism-related discussions

oai_token-act-pair · gemini-2.0-flash

Hotels and lodging

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

writeField

-0.60

Hochspringen

-0.59

GraphicsUnit

-0.57

CROSSTALK

-0.57

存于互联网档案馆

-0.57

SerializedSize

-0.55

 发表于

-0.54

ladi

-0.54

Activité

-0.54

 schuldig

-0.53

POSITIVE LOGITS

 hotel

1.02

 hotels

0.97

 accommodation

0.89

 motel

0.86

hotels

0.84

 lodgings

0.82

Hotels

0.82

 Hotels

0.81

 accommodations

0.81

 Hotel

0.79

Activations Density 3.835%

travel and tourism-related discussions

Hotels and lodging

No Comments

No Known Activations