INDEX

Explanations

code snippets including python and django

oai_token-act-pair · gemini-2.0-flash

py

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

py

-1.91

py

-1.89

Py

-1.88

Py

-1.85

PY

-1.40

PY

-1.23

 Python

-0.92

python

-0.92

Python

-0.92

apy

-0.89

POSITIVE LOGITS

 lệ

0.63

Rhestr

0.60

 vertes

0.57

 VIVO

0.57

Igu

0.57

manera

0.56

EFIAPI

0.55

 Brim

0.55

PREMI

0.54

lapsingToolbar

0.54

Activations Density 2.978%

code snippets including python and django

py

No Comments

No Known Activations