INDEX

Explanations

English prepositions and purchasing information

oai_token-act-pair · gemini-2.0-flash

Possessive pronouns

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

AndEndTag

-0.57

édrale

-0.48

FDRE

-0.47

queryInterface

-0.47

зулта

-0.46

miral

-0.46

AddHtmlAttribute

-0.46

thâu

-0.46

mallows

-0.46

 gynnwys

-0.46

POSITIVE LOGITS

 your

1.24

seu

1.11

 their

1.09

 seus

1.08

 своего

1.06

his

1.05

 своих

1.00

 ihren

0.99

 svých

0.98

 swojego

0.96

Activations Density 1.892%

English prepositions and purchasing information

Possessive pronouns

No Comments

No Known Activations