INDEX

Explanations

the word "just" followed by a direction

oai_token-act-pair · gemini-2.0-flash

Locations

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

yarnpkg

-0.48

 Meksiku

-0.47

üyük

-0.47

 Mine

-0.47

rawdę

-0.47

ælp

-0.46

 nocy

-0.46

tű

-0.45

Pads

-0.45

 günü

-0.44

POSITIVE LOGITS

 AssemblyProduct

0.64

interopRequire

0.61

 initComponents

0.60

 BorderLayout

0.58

rungsseite

0.57

ThroughAttribute

0.56

Obrázky

0.56

ður

0.54

Bioaccumulative

0.54

 חיצוניים

0.52

Activations Density 0.282%

the word "just" followed by a direction

Locations

No Comments

No Known Activations