INDEX

Explanations

newspaper-related terms and section headings

oai_token-act-pair · gemini-2.0-flash

story

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

Fol

-0.43

óleo

-0.42

างเกง

-0.42

Fol

-0.42

skiej

-0.40

 修正

-0.40

 mengajar

-0.40

 kullanılır

-0.39

axial

-0.38

 Desai

-0.38

POSITIVE LOGITS

=$?

0.77

 AssemblyCulture

0.75

encodeWith

0.74

 архивлан

0.72

ArrowToggle

0.71

 autorytatywna

0.68

 שוליים

0.68

</thead>

0.68

="@+

0.67

исленность

0.66

Activations Density 1.423%

newspaper-related terms and section headings

story

No Comments

No Known Activations