INDEX

Explanations

the letter "i" and sometimes "I"

oai_token-act-pair · gemini-2.0-flash

i

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

-2.63

Efq

-1.73

 purpoſe

-1.48

 MainAxisSize

-1.47

 myſelf

-1.46

 Monfieur

-1.44

 poffible

-1.42

 itſelf

-1.41

 Jefus

-1.38

 iſt

-1.35

POSITIVE LOGITS

1.02

0.75

0.69

0.63

<b>

0.60

</i>

0.60

is

0.59

’

0.58

↵

0.58

<eos>

0.57

Activations Density 0.906%

the letter "i" and sometimes "I"

i

No Comments

No Known Activations