INDEX

Explanations

words or phrases that might appear in product descriptions

oai_token-act-pair · gemini-2.0-flash

consumer products

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

 للمعارف

-0.92

ConstraintMaker

-0.91

AddTagHelper

-0.91

TagMode

-0.86

 الحره

-0.84

SequentialGroup

-0.82

ThroughAttribute

-0.81

tvguidetime

-0.80

ChildScrollView

-0.79

TargetException

-0.79

POSITIVE LOGITS

 multi

0.45

 European

0.41

dog

0.40

لیسی

0.40

 simple

0.39

 China

0.39

 South

0.38

 Europe

0.37

double

0.37

multi

0.37

Activations Density 4.874%

words or phrases that might appear in product descriptions

consumer products

No Comments

No Known Activations