INDEX

Explanations

the word "me" and some related pronouns

oai_token-act-pair · gemini-2.0-flash

me

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

me

-2.52

Me

-1.87

Me

-1.87

me

-1.68

ME

-1.43

ME

-1.26

us

-1.11

 conmigo

-0.90

我了

-0.89

 меня

-0.88

POSITIVE LOGITS

ModelAdmin

0.72

 resourceCulture

0.70

fjspx

0.69

webElementXpaths

0.64

ientôt

0.61

DataSnapshot

0.59

 dataSnapshot

0.59

})`

0.59

:✨

0.58

writeFieldEnd

0.56

Activations Density 1.478%

the word "me" and some related pronouns

me

No Comments

No Known Activations