INDEX

Explanations

a variety of words that it has been trained on

oai_token-act-pair · gemini-2.0-flash

Enthusiasm/Interest

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 StatefulWidget

-0.49

AndEndTag

-0.47

nek

-0.42

 خارجية

-0.40

LES

-0.39

MetaObject

-0.39

ok

-0.38

 complete

-0.38

execSQL

-0.38

enskap

-0.37

POSITIVE LOGITS

 تضيفلها

0.91

UnsafeEnabled

0.74

jsii

0.67

lorette

0.64

 meiosis

0.63

GRAFÍA

0.62

rillation

0.62

rrggbb

0.62

 kube

0.62

ípio

0.60

Activations Density 24.580%

a variety of words that it has been trained on

Enthusiasm/Interest

No Comments

No Known Activations