INDEX

Explanations

python code related to Django models and database definitions

oai_token-act-pair · gemini-2.0-flash

code snippets

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 pinulongan

-0.83

帖最后由

-0.71

aarrggbb

-0.66

tvguidetime

-0.66

ValueGeneration

-0.66

DebuggerStep

-0.65

principalColumn

-0.64

oa̍t

-0.64

 Superhost

-0.60

 kaarangay

-0.60

POSITIVE LOGITS

enerys

0.46

 apri

0.46

hock

0.45

odymium

0.45

bitur

0.45

CAST

0.44

Cast

0.44

 Cardi

0.43

 Cáceres

0.43

cast

0.42

Activations Density 0.153%

python code related to Django models and database definitions

code snippets

No Comments

No Known Activations