INDEX

Explanations

code snippets that define functions and handle http responses

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_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

SourceChecksum

-1.17

 pleaſure

-1.13

parsedMessage

-1.13

 raiſ

-1.09

rungsseite

-1.06

 ſeveral

-1.05

 itſelf

-1.05

 كومونز

-1.04

 myſelf

-1.02

 насељу

-1.00

POSITIVE LOGITS

is

0.40

MD

0.39

 esimer

0.38

IS

0.35

RL

0.35

รม

0.35

اب

0.34

רצ

0.34

Activations Density 1.299%

code snippets that define functions and handle http responses

Code snippets

No Comments

No Known Activations