INDEX

Explanations

phrases using "have", "has", "had", "its", and "without"

oai_token-act-pair · gemini-2.0-flash

own

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

 base

-1.30

 bases

-1.28

bases

-1.17

base

-1.15

 BASED

-1.10

 based

-1.06

 Base

-1.05

 Bases

-1.05

 Based

-1.00

 basing

-0.98

POSITIVE LOGITS

own

0.53

ups

0.52

Sco

0.49

 épo

0.48

Sco

0.47

 berupa

0.47

EMON

0.47

 своя

0.46

 نزد

0.45

ไ

0.45

Activations Density 0.742%

phrases using "have", "has", "had", "its", and "without"

own

No Comments

No Known Activations